Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
e2909b33
Commit
e2909b33
authored
Feb 26, 2024
by
haileyschoelkopf
Browse files
transfer zeroshot improvements on bbh to fewshot
parent
96d185fa
Changes
56
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
464 additions
and
12 deletions
+464
-12
lm_eval/tasks/bbh/cot_fewshot/snarks.yaml
lm_eval/tasks/bbh/cot_fewshot/snarks.yaml
+15
-1
lm_eval/tasks/bbh/cot_fewshot/sports_understanding.yaml
lm_eval/tasks/bbh/cot_fewshot/sports_understanding.yaml
+16
-1
lm_eval/tasks/bbh/cot_fewshot/temporal_sequences.yaml
lm_eval/tasks/bbh/cot_fewshot/temporal_sequences.yaml
+15
-1
lm_eval/tasks/bbh/cot_fewshot/tracking_shuffled_objects_five_objects.yaml
...h/cot_fewshot/tracking_shuffled_objects_five_objects.yaml
+15
-1
lm_eval/tasks/bbh/cot_fewshot/tracking_shuffled_objects_seven_objects.yaml
.../cot_fewshot/tracking_shuffled_objects_seven_objects.yaml
+15
-1
lm_eval/tasks/bbh/cot_fewshot/tracking_shuffled_objects_three_objects.yaml
.../cot_fewshot/tracking_shuffled_objects_three_objects.yaml
+15
-1
lm_eval/tasks/bbh/cot_fewshot/utils.py
lm_eval/tasks/bbh/cot_fewshot/utils.py
+224
-0
lm_eval/tasks/bbh/cot_fewshot/web_of_lies.yaml
lm_eval/tasks/bbh/cot_fewshot/web_of_lies.yaml
+16
-1
lm_eval/tasks/bbh/cot_fewshot/word_sorting.yaml
lm_eval/tasks/bbh/cot_fewshot/word_sorting.yaml
+11
-1
lm_eval/tasks/bbh/fewshot/_fewshot_template_yaml
lm_eval/tasks/bbh/fewshot/_fewshot_template_yaml
+10
-4
lm_eval/tasks/bbh/fewshot/boolean_expressions.yaml
lm_eval/tasks/bbh/fewshot/boolean_expressions.yaml
+10
-0
lm_eval/tasks/bbh/fewshot/causal_judgement.yaml
lm_eval/tasks/bbh/fewshot/causal_judgement.yaml
+10
-0
lm_eval/tasks/bbh/fewshot/date_understanding.yaml
lm_eval/tasks/bbh/fewshot/date_understanding.yaml
+12
-0
lm_eval/tasks/bbh/fewshot/disambiguation_qa.yaml
lm_eval/tasks/bbh/fewshot/disambiguation_qa.yaml
+12
-0
lm_eval/tasks/bbh/fewshot/dyck_languages.yaml
lm_eval/tasks/bbh/fewshot/dyck_languages.yaml
+10
-0
lm_eval/tasks/bbh/fewshot/formal_fallacies.yaml
lm_eval/tasks/bbh/fewshot/formal_fallacies.yaml
+10
-0
lm_eval/tasks/bbh/fewshot/geometric_shapes.yaml
lm_eval/tasks/bbh/fewshot/geometric_shapes.yaml
+12
-0
lm_eval/tasks/bbh/fewshot/hyperbaton.yaml
lm_eval/tasks/bbh/fewshot/hyperbaton.yaml
+12
-0
lm_eval/tasks/bbh/fewshot/logical_deduction_five_objects.yaml
...val/tasks/bbh/fewshot/logical_deduction_five_objects.yaml
+12
-0
lm_eval/tasks/bbh/fewshot/logical_deduction_seven_objects.yaml
...al/tasks/bbh/fewshot/logical_deduction_seven_objects.yaml
+12
-0
No files found.
lm_eval/tasks/bbh/cot_fewshot/snarks.yaml
View file @
e2909b33
"
dataset_name"
:
"
snarks"
"
dataset_name"
:
"
snarks"
"
description"
:
"
Determine
which
of
two
sentences
is
sarcastic.
\n\n
According
to
Cambridge
University
Dictionary,
sarcasm
is
\"
the
use
of
remarks
that
clearly
mean
the
opposite
of
what
they
say,
made
in
order
to
hurt
someone's
feelings
or
to
criticize
something
in
a
humorous
way.
\"
Sarcastic
sentences
often
contain
satirical
or
ironic
utterances,
hyperboles,
ambivalent
or
witty
remarks.
\n\n
"
"
description"
:
"
Determine
which
of
two
sentences
is
sarcastic.
\n\n
According
to
Cambridge
University
Dictionary,
sarcasm
is
\"
the
use
of
remarks
that
clearly
mean
the
opposite
of
what
they
say,
made
in
order
to
hurt
someone's
feelings
or
to
criticize
something
in
a
humorous
way.
\"
Sarcastic
sentences
often
contain
satirical
or
ironic
utterances,
hyperboles,
ambivalent
or
witty
remarks.
\n\n
"
"
doc_to_text"
:
"
Q:
Which
statement
is
sarcastic?
\n
Options:
\n
(A)
Yes,
because
having
interests
and
actively
researching
them
is
a
huge
waste
\n
(B)
Yes,
because
having
interests
and
actively
researching
them
is
a
huge
deal
\n
A:
Let's
think
step
by
step.
\n
If
we
look
at
(A),
it
says
that
having
interests
and
actively
researching
them
is
a
huge
waste,
implying
that
it
is
a
useless
effort.
However,
we
know
that
having
interests
and
actively
researching
them
is
typically
not
a
waste
but
rather
is
beneficial
to
the
individual.
The
presence
of
such
a
juxtaposition
in
(A)
suggests
that
it
contains
a
taste
of
irony
and
sarcasm.
\n
If
we
look
at
(B),
it
says
that
having
interests
and
actively
researching
them
is
a
huge
deal,
implying
that
it
is
an
important
and
consequential
effort.
This
is
arguably
a
neutral
and
correct
statement.
\n
Above
the
above,
the
sarcastic
option
is
(A).
So
the
answer
is
(A).
\n\n
Q:
Which
statement
is
sarcastic?
\n
Options:
\n
(A)
No
one
is
going
to
disagree
with
you
on
this.
Avoiding
ad
hominem
attacks
really
help
your
case
\n
(B)
No
one
is
going
to
disagree
with
you
on
this.
Ad
hominem
attacks
really
help
your
case
\n
A:
Let's
think
step
by
step.
\n
If
we
look
at
(A),
it
says
that
avoiding
ad
hominem
attacks
really
help
your
case,
implying
that
ad
hominem
attacks
are
adverse
and
injurious.
Because
ad
hominem
attacks
are
adressed
at
a
person
rather
than
an
idea,
it
is
indeed
true
that
avoiding
them
is
often
useful
and
helpful;
so,
(A)
is
a
neutral
(valid
and
agreeable)
statement.
\n
If
we
look
at
(B),
it
says
that
ad
hominem
attacks
really
help
your
case,
implying
that
ad
hominem
attacks
are
a
positive
thing.
However,
we
stated
previously
that
ad
hominem
attacks
are
often
not
useful
or
constructive.
The
speaker
in
this
sentence
therefore
seems
to
mean
the
opposite
of
what
they
are
saying;
so,
there
appears
to
have
a
taste
of
irony
and
sarcasm
in
(B).
\n
Above
the
above,
the
sarcastic
option
is
(B).
So
the
answer
is
(B).
\n\n
Q:
Which
statement
is
sarcastic?
\n
Options:
\n
(A)
Consistency
in
the
league's
punishments?
What
do
you
think
this
is
supposed
to
be,
politics?
\n
(B)
Consistency
in
the
league's
punishments?
What
do
you
think
this
is
supposed
to
be,
moral?
\n
A:
Let's
think
step
by
step.
\n
If
we
look
at
(A),
it
likens
the
consistency
in
the
league's
punishments
with
that
in
politics.
Because
politics
or
political
affairs
are
often
not
considered
to
be
consistent
or
dependable,
this
sentence
appears
to
be
satirical.
\n
If
we
look
at
(B),
it
likens
the
consistency
in
the
league's
punishments
with
that
in
morality.
Discussing
the
consistency
of
the
league's
punishments
in
the
context
of
morality,
ethics,
or
law
makes
sense
and
does
not
appear
to
make
a
satirical
point
about
anything.
\n
Above
the
above,
the
sarcastic
option
is
(A).
So
the
answer
is
(A).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step.
\n
"
"
doc_to_text"
:
"
Q:
Which
statement
is
sarcastic?
\n
Options:
\n
(A)
Yes,
because
having
interests
and
actively
researching
them
is
a
huge
waste
\n
(B)
Yes,
because
having
interests
and
actively
researching
them
is
a
huge
deal
\n
A:
Let's
think
step
by
step.
\n
If
we
look
at
(A),
it
says
that
having
interests
and
actively
researching
them
is
a
huge
waste,
implying
that
it
is
a
useless
effort.
However,
we
know
that
having
interests
and
actively
researching
them
is
typically
not
a
waste
but
rather
is
beneficial
to
the
individual.
The
presence
of
such
a
juxtaposition
in
(A)
suggests
that
it
contains
a
taste
of
irony
and
sarcasm.
\n
If
we
look
at
(B),
it
says
that
having
interests
and
actively
researching
them
is
a
huge
deal,
implying
that
it
is
an
important
and
consequential
effort.
This
is
arguably
a
neutral
and
correct
statement.
\n
Above
the
above,
the
sarcastic
option
is
(A).
So
the
answer
is
(A).
\n\n
Q:
Which
statement
is
sarcastic?
\n
Options:
\n
(A)
No
one
is
going
to
disagree
with
you
on
this.
Avoiding
ad
hominem
attacks
really
help
your
case
\n
(B)
No
one
is
going
to
disagree
with
you
on
this.
Ad
hominem
attacks
really
help
your
case
\n
A:
Let's
think
step
by
step.
\n
If
we
look
at
(A),
it
says
that
avoiding
ad
hominem
attacks
really
help
your
case,
implying
that
ad
hominem
attacks
are
adverse
and
injurious.
Because
ad
hominem
attacks
are
adressed
at
a
person
rather
than
an
idea,
it
is
indeed
true
that
avoiding
them
is
often
useful
and
helpful;
so,
(A)
is
a
neutral
(valid
and
agreeable)
statement.
\n
If
we
look
at
(B),
it
says
that
ad
hominem
attacks
really
help
your
case,
implying
that
ad
hominem
attacks
are
a
positive
thing.
However,
we
stated
previously
that
ad
hominem
attacks
are
often
not
useful
or
constructive.
The
speaker
in
this
sentence
therefore
seems
to
mean
the
opposite
of
what
they
are
saying;
so,
there
appears
to
have
a
taste
of
irony
and
sarcasm
in
(B).
\n
Above
the
above,
the
sarcastic
option
is
(B).
So
the
answer
is
(B).
\n\n
Q:
Which
statement
is
sarcastic?
\n
Options:
\n
(A)
Consistency
in
the
league's
punishments?
What
do
you
think
this
is
supposed
to
be,
politics?
\n
(B)
Consistency
in
the
league's
punishments?
What
do
you
think
this
is
supposed
to
be,
moral?
\n
A:
Let's
think
step
by
step.
\n
If
we
look
at
(A),
it
likens
the
consistency
in
the
league's
punishments
with
that
in
politics.
Because
politics
or
political
affairs
are
often
not
considered
to
be
consistent
or
dependable,
this
sentence
appears
to
be
satirical.
\n
If
we
look
at
(B),
it
likens
the
consistency
in
the
league's
punishments
with
that
in
morality.
Discussing
the
consistency
of
the
league's
punishments
in
the
context
of
morality,
ethics,
or
law
makes
sense
and
does
not
appear
to
make
a
satirical
point
about
anything.
\n
Above
the
above,
the
sarcastic
option
is
(A).
So
the
answer
is
(A).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step."
"
include"
:
"
_cot_fewshot_template_yaml"
"
include"
:
"
_cot_fewshot_template_yaml"
"
task"
:
"
bbh_cot_fewshot_snarks"
"
task"
:
"
bbh_cot_fewshot_snarks"
filter_list
:
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
-1
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
-
name
:
"
strict-match"
filter
:
-
function
:
"
regex"
regex_pattern
:
"
((?<=The
answer
is
)(.*)(?=.)|(?<=the
answer
is
)(.*)(?=.)|(?<=The
answer:
)(.*)(?=.)|(?<=The
final
answer:
)(.*)(?=.))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/cot_fewshot/sports_understanding.yaml
View file @
e2909b33
"
dataset_name"
:
"
sports_understanding"
"
dataset_name"
:
"
sports_understanding"
"
description"
:
"
Determine
whether
an
artificially
constructed
sentence
relating
to
sports
is
plausible
or
not.
\n\n
"
"
description"
:
"
Determine
whether
an
artificially
constructed
sentence
relating
to
sports
is
plausible
or
not.
\n\n
"
"
doc_to_text"
:
"
Q:
Is
the
following
sentence
plausible?
\"
Bam
Adebayo
scored
a
reverse
layup
in
the
Western
Conference
Finals.
\"\n
A:
Let's
think
step
by
step.
Bam
Adebayo
is
an
American
basketball
player.
Scoring
a
reverse
layup
in
the
Western
Conference
Finals
is
part
of
the
NBA
Finals.
So
the
answer
is
yes.
\n\n
Q:
Is
the
following
sentence
plausible?
\"
Santi
Cazorla
scored
a
touchdown.
\"\n
A:
Let's
think
step
by
step.
Santi
Cazorla
is
a
soccer
player.
Touchdown
is
part
of
American
football
and
rugby.
So
the
answer
is
no.
\n\n
Q:
Is
the
following
sentence
plausible?
\"
DeMar
DeRozan
was
called
for
the
goal
tend.
\"\n
A:
Let's
think
step
by
step.
DeMar
DeRozan
is
an
American
basketball
player.
Goal
tending
is
part
of
basketball.
So
the
answer
is
yes.
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step.
\n
"
"
doc_to_text"
:
"
Q:
Is
the
following
sentence
plausible?
\"
Bam
Adebayo
scored
a
reverse
layup
in
the
Western
Conference
Finals.
\"\n
A:
Let's
think
step
by
step.
Bam
Adebayo
is
an
American
basketball
player.
Scoring
a
reverse
layup
in
the
Western
Conference
Finals
is
part
of
the
NBA
Finals.
So
the
answer
is
yes.
\n\n
Q:
Is
the
following
sentence
plausible?
\"
Santi
Cazorla
scored
a
touchdown.
\"\n
A:
Let's
think
step
by
step.
Santi
Cazorla
is
a
soccer
player.
Touchdown
is
part
of
American
football
and
rugby.
So
the
answer
is
no.
\n\n
Q:
Is
the
following
sentence
plausible?
\"
DeMar
DeRozan
was
called
for
the
goal
tend.
\"\n
A:
Let's
think
step
by
step.
DeMar
DeRozan
is
an
American
basketball
player.
Goal
tending
is
part
of
basketball.
So
the
answer
is
yes.
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step."
"
include"
:
"
_cot_fewshot_template_yaml"
"
include"
:
"
_cot_fewshot_template_yaml"
"
task"
:
"
bbh_cot_fewshot_sports_understanding"
"
task"
:
"
bbh_cot_fewshot_sports_understanding"
filter_list
:
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MapRegexFilter
group_select
:
-1
ignore_case
:
true
regex_pattern_to_value
:
\b(no|not plausible)\b
:
"
no"
\b(yes|plausible)\b
:
"
yes"
-
function
:
"
take_first"
-
name
:
"
strict-match"
filter
:
-
function
:
"
regex"
regex_pattern
:
"
((?<=The
answer
is
)(.*)(?=.)|(?<=the
answer
is
)(.*)(?=.)|(?<=The
answer:
)(.*)(?=.)|(?<=The
final
answer:
)(.*)(?=.))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/cot_fewshot/temporal_sequences.yaml
View file @
e2909b33
"
dataset_name"
:
"
temporal_sequences"
"
dataset_name"
:
"
temporal_sequences"
"
description"
:
"
Task
description:
Answer
questions
about
which
times
certain
events
could
have
occurred.
\n\n
"
"
description"
:
"
Task
description:
Answer
questions
about
which
times
certain
events
could
have
occurred.
\n\n
"
"
doc_to_text"
:
"
Q:
Today,
Emily
went
to
the
museum.
Between
what
times
could
they
have
gone?
\n
We
know
that:
\n
Emily
woke
up
at
1pm.
\n
Elizabeth
saw
Emily
reading
at
the
library
from
2pm
to
4pm.
\n
Jessica
saw
Emily
watching
a
movie
at
the
theater
from
4pm
to
5pm.
\n
Leslie
saw
Emily
waiting
at
the
airport
from
5pm
to
6pm.
\n
William
saw
Emily
buying
clothes
at
the
mall
from
6pm
to
7pm.
\n
The
museum
was
closed
after
7pm.
\n
Between
what
times
could
Emily
have
gone
to
the
museum?
\n
Options:
\n
(A)
1pm
to
2pm
\n
(B)
6pm
to
7pm
\n
(C)
5pm
to
6pm
\n
(D)
2pm
to
4pm
\n
A:
Let's
think
step
by
step.
\n
Wake-up
time:
1pm.
\n
1pm-2pm:
free.
\n
2pm-4pm:
reading
at
the
library.
\n
4pm-5pm:
watching
a
movie
at
the
theater.
\n
5pm-6pm:
waiting
at
the
airport.
\n
6pm-7pm:
buying
clothes
at
the
mall.
\n
The
museum
closure
time:
7pm.
\n
The
only
time
when
Emily
could
have
gone
to
the
museum
was
1pm
to
2pm.
So
the
answer
is
(A).
\n\n
Q:
Today,
Elizabeth
went
to
the
amusement
park.
Between
what
times
could
they
have
gone?
\n
We
know
that:
\n
Elizabeth
woke
up
at
7am.
\n
David
saw
Elizabeth
fixing
their
computer
at
the
electronic
store
from
1pm
to
2pm.
\n
Sarah
saw
Elizabeth
playing
tennis
at
the
tennis
court
from
2pm
to
3pm.
\n
Susan
saw
Elizabeth
walking
towards
the
Statue
of
Liberty
from
3pm
to
6pm.
\n
Andrew
saw
Elizabeth
taking
photos
near
the
Eiffel
Tower
from
6pm
to
9pm.
\n
Emily
saw
Elizabeth
getting
a
coffee
at
the
cafe
from
9pm
to
10pm.
\n
The
amusement
park
was
closed
after
10pm.
\n
Between
what
times
could
Elizabeth
have
gone
to
the
amusement
park?
\n
Options:
\n
(A)
7am
to
1pm
\n
(B)
9pm
to
10pm
\n
(C)
1pm
to
2pm
\n
(D)
3pm
to
6pm
\n
A:
Let's
think
step
by
step.
\n
Wake-up
time:
7am.
\n
7am-1pm:
free.
\n
1pm-2pm:
fixing
their
computer
at
the
electronic
store.
\n
2pm-3pm:
playing
tennis
at
the
tennis
court.
\n
3pm-6pm:
walking
towards
the
Statue
of
Liberty.
\n
6pm-9pm:
taking
photos
near
the
Eiffel
Tower.
\n
9pm-10pm:
getting
a
coffee
at
the
cafe.
\n
The
amusement
park
closure
time:
10pm.
\n
The
only
time
when
Elizabeth
could
have
gone
to
the
amusement
park
was
7am
to
1pm.
So
the
answer
is
(A).
\n\n
Q:
Today,
Tiffany
went
to
the
beach.
Between
what
times
could
they
have
gone?
\n
We
know
that:
\n
Tiffany
woke
up
at
5am.
\n
Betty
saw
Tiffany
getting
a
coffee
at
the
cafe
from
5am
to
6am.
\n
Jessica
saw
Tiffany
working
at
the
office
from
6am
to
9am.
\n
John
saw
Tiffany
stretching
at
a
yoga
studio
from
9am
to
12pm.
\n
Sean
saw
Tiffany
sitting
on
a
rooftop
from
12pm
to
2pm.
\n
Sarah
saw
Tiffany
playing
tennis
at
the
tennis
court
from
2pm
to
3pm.
\n
The
beach
was
closed
after
4pm.
\n
Between
what
times
could
Tiffany
have
gone
to
the
beach?
\n
Options:
\n
(A)
9am
to
12pm
\n
(B)
12pm
to
2pm
\n
(C)
5am
to
6am
\n
(D)
3pm
to
4pm
\n
A:
Let's
think
step
by
step.
\n
Wake-up
time:
5am.
\n
5am-6am:
getting
a
coffee
at
the
cafe.
\n
6am-9am:
working
at
the
office.
\n
9am-12pm:
stretching
at
a
yoga
studio.
\n
12pm-2pm:
sitting
on
a
rooftop.
\n
2pm-3pm:
playing
tennis
at
the
tennis
court.
\n
3pm-4pm:
free.
\n
The
beach
closure
time:
4pm.
\n
The
only
time
when
Tiffany
could
have
gone
to
the
beach
was
3pm
to
4pm.
So
the
answer
is
(D).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step.
\n
"
"
doc_to_text"
:
"
Q:
Today,
Emily
went
to
the
museum.
Between
what
times
could
they
have
gone?
\n
We
know
that:
\n
Emily
woke
up
at
1pm.
\n
Elizabeth
saw
Emily
reading
at
the
library
from
2pm
to
4pm.
\n
Jessica
saw
Emily
watching
a
movie
at
the
theater
from
4pm
to
5pm.
\n
Leslie
saw
Emily
waiting
at
the
airport
from
5pm
to
6pm.
\n
William
saw
Emily
buying
clothes
at
the
mall
from
6pm
to
7pm.
\n
The
museum
was
closed
after
7pm.
\n
Between
what
times
could
Emily
have
gone
to
the
museum?
\n
Options:
\n
(A)
1pm
to
2pm
\n
(B)
6pm
to
7pm
\n
(C)
5pm
to
6pm
\n
(D)
2pm
to
4pm
\n
A:
Let's
think
step
by
step.
\n
Wake-up
time:
1pm.
\n
1pm-2pm:
free.
\n
2pm-4pm:
reading
at
the
library.
\n
4pm-5pm:
watching
a
movie
at
the
theater.
\n
5pm-6pm:
waiting
at
the
airport.
\n
6pm-7pm:
buying
clothes
at
the
mall.
\n
The
museum
closure
time:
7pm.
\n
The
only
time
when
Emily
could
have
gone
to
the
museum
was
1pm
to
2pm.
So
the
answer
is
(A).
\n\n
Q:
Today,
Elizabeth
went
to
the
amusement
park.
Between
what
times
could
they
have
gone?
\n
We
know
that:
\n
Elizabeth
woke
up
at
7am.
\n
David
saw
Elizabeth
fixing
their
computer
at
the
electronic
store
from
1pm
to
2pm.
\n
Sarah
saw
Elizabeth
playing
tennis
at
the
tennis
court
from
2pm
to
3pm.
\n
Susan
saw
Elizabeth
walking
towards
the
Statue
of
Liberty
from
3pm
to
6pm.
\n
Andrew
saw
Elizabeth
taking
photos
near
the
Eiffel
Tower
from
6pm
to
9pm.
\n
Emily
saw
Elizabeth
getting
a
coffee
at
the
cafe
from
9pm
to
10pm.
\n
The
amusement
park
was
closed
after
10pm.
\n
Between
what
times
could
Elizabeth
have
gone
to
the
amusement
park?
\n
Options:
\n
(A)
7am
to
1pm
\n
(B)
9pm
to
10pm
\n
(C)
1pm
to
2pm
\n
(D)
3pm
to
6pm
\n
A:
Let's
think
step
by
step.
\n
Wake-up
time:
7am.
\n
7am-1pm:
free.
\n
1pm-2pm:
fixing
their
computer
at
the
electronic
store.
\n
2pm-3pm:
playing
tennis
at
the
tennis
court.
\n
3pm-6pm:
walking
towards
the
Statue
of
Liberty.
\n
6pm-9pm:
taking
photos
near
the
Eiffel
Tower.
\n
9pm-10pm:
getting
a
coffee
at
the
cafe.
\n
The
amusement
park
closure
time:
10pm.
\n
The
only
time
when
Elizabeth
could
have
gone
to
the
amusement
park
was
7am
to
1pm.
So
the
answer
is
(A).
\n\n
Q:
Today,
Tiffany
went
to
the
beach.
Between
what
times
could
they
have
gone?
\n
We
know
that:
\n
Tiffany
woke
up
at
5am.
\n
Betty
saw
Tiffany
getting
a
coffee
at
the
cafe
from
5am
to
6am.
\n
Jessica
saw
Tiffany
working
at
the
office
from
6am
to
9am.
\n
John
saw
Tiffany
stretching
at
a
yoga
studio
from
9am
to
12pm.
\n
Sean
saw
Tiffany
sitting
on
a
rooftop
from
12pm
to
2pm.
\n
Sarah
saw
Tiffany
playing
tennis
at
the
tennis
court
from
2pm
to
3pm.
\n
The
beach
was
closed
after
4pm.
\n
Between
what
times
could
Tiffany
have
gone
to
the
beach?
\n
Options:
\n
(A)
9am
to
12pm
\n
(B)
12pm
to
2pm
\n
(C)
5am
to
6am
\n
(D)
3pm
to
4pm
\n
A:
Let's
think
step
by
step.
\n
Wake-up
time:
5am.
\n
5am-6am:
getting
a
coffee
at
the
cafe.
\n
6am-9am:
working
at
the
office.
\n
9am-12pm:
stretching
at
a
yoga
studio.
\n
12pm-2pm:
sitting
on
a
rooftop.
\n
2pm-3pm:
playing
tennis
at
the
tennis
court.
\n
3pm-4pm:
free.
\n
The
beach
closure
time:
4pm.
\n
The
only
time
when
Tiffany
could
have
gone
to
the
beach
was
3pm
to
4pm.
So
the
answer
is
(D).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step."
"
include"
:
"
_cot_fewshot_template_yaml"
"
include"
:
"
_cot_fewshot_template_yaml"
"
task"
:
"
bbh_cot_fewshot_temporal_sequences"
"
task"
:
"
bbh_cot_fewshot_temporal_sequences"
filter_list
:
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
-1
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
-
name
:
"
strict-match"
filter
:
-
function
:
"
regex"
regex_pattern
:
"
((?<=The
answer
is
)(.*)(?=.)|(?<=the
answer
is
)(.*)(?=.)|(?<=The
answer:
)(.*)(?=.)|(?<=The
final
answer:
)(.*)(?=.))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/cot_fewshot/tracking_shuffled_objects_five_objects.yaml
View file @
e2909b33
"
dataset_name"
:
"
tracking_shuffled_objects_five_objects"
"
dataset_name"
:
"
tracking_shuffled_objects_five_objects"
"
description"
:
"
A
task
requiring
determining
the
final
positions
of
a
set
of
objects
given
their
initial
positions
and
a
description
of
a
sequence
of
swaps.
\n\n
"
"
description"
:
"
A
task
requiring
determining
the
final
positions
of
a
set
of
objects
given
their
initial
positions
and
a
description
of
a
sequence
of
swaps.
\n\n
"
"
doc_to_text"
:
"
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
yellow
ball,
Bob
has
a
blue
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Claire
and
Alice
swap
balls.
Then,
Alice
and
Bob
swap
balls.
Finally,
Claire
and
Bob
swap
balls.
At
the
end
of
the
game,
Bob
has
the
\n
Options:
\n
(A)
yellow
ball
\n
(B)
blue
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
yellow,
Bob:
blue,
Claire:
pink.
\n
(1)
Claire
and
Alice
swap
balls:
Alice:
pink,
Bob:
blue,
Claire:
yellow.
\n
(2)
Alice
and
Bob
swap
balls:
Alice:
blue,
Bob:
pink,
Claire:
yellow.
\n
(3)
Claire
and
Bob
swap
balls:
Alice:
blue,
Bob:
yellow,
Claire:
pink.
\n
At
the
end
of
the
game,
Bob
has
the
yellow
ball.
So
the
answer
is
(A).
\n\n
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
white
ball,
Bob
has
a
purple
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Bob
and
Alice
swap
balls.
Then,
Bob
and
Claire
swap
balls.
Finally,
Bob
and
Alice
swap
balls.
At
the
end
of
the
game,
Alice
has
the
\n
Options:
\n
(A)
white
ball
\n
(B)
purple
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
white,
Bob:
purple,
Claire:
pink.
\n
(1)
Bob
and
Alice
swap
balls:
Alice:
purple,
Bob:
white,
Claire:
pink.
\n
(2)
Bob
and
Claire
swap
balls:
Alice:
purple,
Bob:
pink,
Claire:
white.
\n
(3)
Bob
and
Alice
swap
balls:
Alice:
pink,
Bob:
purple,
Claire:
white.
\n
At
the
end
of
the
game,
Alice
has
the
pink
ball.
So
the
answer
is
(C).
\n\n
Q:
Alice,
Bob,
and
Claire
are
dancers
at
a
square
dance.
At
the
start
of
a
song,
they
each
have
a
partner:
Alice
is
dancing
with
Lola,
Bob
is
dancing
with
Rodrigo,
and
Claire
is
dancing
with
Patrick.
\n
Throughout
the
song,
the
dancers
often
trade
partners.
First,
Alice
and
Bob
switch
partners.
Then,
Claire
and
Bob
switch
partners.
Finally,
Bob
and
Alice
switch
partners.
At
the
end
of
the
dance,
Alice
is
dancing
with
\n
Options:
\n
(A)
Lola
\n
(B)
Rodrigo
\n
(C)
Patrick
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
Lola,
Bob:
Rodrigo,
Claire:
Patrick.
\n
(1)
Alice
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Lola,
Claire:
Patrick.
\n
(2)
Claire
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Patrick,
Claire:
Lola.
\n
(3)
Bob
and
Alice
switch
partners:
Alice:
Patrick,
Bob:
Rodrigo,
Claire:
Lola.
\n
At
the
end
of
the
dance,
Alice
is
dancing
with
Patrick.
So
the
answer
is
(C).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step.
\n
"
"
doc_to_text"
:
"
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
yellow
ball,
Bob
has
a
blue
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Claire
and
Alice
swap
balls.
Then,
Alice
and
Bob
swap
balls.
Finally,
Claire
and
Bob
swap
balls.
At
the
end
of
the
game,
Bob
has
the
\n
Options:
\n
(A)
yellow
ball
\n
(B)
blue
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
yellow,
Bob:
blue,
Claire:
pink.
\n
(1)
Claire
and
Alice
swap
balls:
Alice:
pink,
Bob:
blue,
Claire:
yellow.
\n
(2)
Alice
and
Bob
swap
balls:
Alice:
blue,
Bob:
pink,
Claire:
yellow.
\n
(3)
Claire
and
Bob
swap
balls:
Alice:
blue,
Bob:
yellow,
Claire:
pink.
\n
At
the
end
of
the
game,
Bob
has
the
yellow
ball.
So
the
answer
is
(A).
\n\n
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
white
ball,
Bob
has
a
purple
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Bob
and
Alice
swap
balls.
Then,
Bob
and
Claire
swap
balls.
Finally,
Bob
and
Alice
swap
balls.
At
the
end
of
the
game,
Alice
has
the
\n
Options:
\n
(A)
white
ball
\n
(B)
purple
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
white,
Bob:
purple,
Claire:
pink.
\n
(1)
Bob
and
Alice
swap
balls:
Alice:
purple,
Bob:
white,
Claire:
pink.
\n
(2)
Bob
and
Claire
swap
balls:
Alice:
purple,
Bob:
pink,
Claire:
white.
\n
(3)
Bob
and
Alice
swap
balls:
Alice:
pink,
Bob:
purple,
Claire:
white.
\n
At
the
end
of
the
game,
Alice
has
the
pink
ball.
So
the
answer
is
(C).
\n\n
Q:
Alice,
Bob,
and
Claire
are
dancers
at
a
square
dance.
At
the
start
of
a
song,
they
each
have
a
partner:
Alice
is
dancing
with
Lola,
Bob
is
dancing
with
Rodrigo,
and
Claire
is
dancing
with
Patrick.
\n
Throughout
the
song,
the
dancers
often
trade
partners.
First,
Alice
and
Bob
switch
partners.
Then,
Claire
and
Bob
switch
partners.
Finally,
Bob
and
Alice
switch
partners.
At
the
end
of
the
dance,
Alice
is
dancing
with
\n
Options:
\n
(A)
Lola
\n
(B)
Rodrigo
\n
(C)
Patrick
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
Lola,
Bob:
Rodrigo,
Claire:
Patrick.
\n
(1)
Alice
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Lola,
Claire:
Patrick.
\n
(2)
Claire
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Patrick,
Claire:
Lola.
\n
(3)
Bob
and
Alice
switch
partners:
Alice:
Patrick,
Bob:
Rodrigo,
Claire:
Lola.
\n
At
the
end
of
the
dance,
Alice
is
dancing
with
Patrick.
So
the
answer
is
(C).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step."
"
include"
:
"
_cot_fewshot_template_yaml"
"
include"
:
"
_cot_fewshot_template_yaml"
"
task"
:
"
bbh_cot_fewshot_tracking_shuffled_objects_five_objects"
"
task"
:
"
bbh_cot_fewshot_tracking_shuffled_objects_five_objects"
filter_list
:
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
-1
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
-
name
:
"
strict-match"
filter
:
-
function
:
"
regex"
regex_pattern
:
"
((?<=The
answer
is
)(.*)(?=.)|(?<=the
answer
is
)(.*)(?=.)|(?<=The
answer:
)(.*)(?=.)|(?<=The
final
answer:
)(.*)(?=.))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/cot_fewshot/tracking_shuffled_objects_seven_objects.yaml
View file @
e2909b33
"
dataset_name"
:
"
tracking_shuffled_objects_seven_objects"
"
dataset_name"
:
"
tracking_shuffled_objects_seven_objects"
"
description"
:
"
A
task
requiring
determining
the
final
positions
of
a
set
of
objects
given
their
initial
positions
and
a
description
of
a
sequence
of
swaps.
\n\n
"
"
description"
:
"
A
task
requiring
determining
the
final
positions
of
a
set
of
objects
given
their
initial
positions
and
a
description
of
a
sequence
of
swaps.
\n\n
"
"
doc_to_text"
:
"
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
yellow
ball,
Bob
has
a
blue
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Claire
and
Alice
swap
balls.
Then,
Alice
and
Bob
swap
balls.
Finally,
Claire
and
Bob
swap
balls.
At
the
end
of
the
game,
Bob
has
the
\n
Options:
\n
(A)
yellow
ball
\n
(B)
blue
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
yellow,
Bob:
blue,
Claire:
pink.
\n
(1)
Claire
and
Alice
swap
balls:
Alice:
pink,
Bob:
blue,
Claire:
yellow.
\n
(2)
Alice
and
Bob
swap
balls:
Alice:
blue,
Bob:
pink,
Claire:
yellow.
\n
(3)
Claire
and
Bob
swap
balls:
Alice:
blue,
Bob:
yellow,
Claire:
pink.
\n
At
the
end
of
the
game,
Bob
has
the
yellow
ball.
So
the
answer
is
(A).
\n\n
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
white
ball,
Bob
has
a
purple
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Bob
and
Alice
swap
balls.
Then,
Bob
and
Claire
swap
balls.
Finally,
Bob
and
Alice
swap
balls.
At
the
end
of
the
game,
Alice
has
the
\n
Options:
\n
(A)
white
ball
\n
(B)
purple
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
white,
Bob:
purple,
Claire:
pink.
\n
(1)
Bob
and
Alice
swap
balls:
Alice:
purple,
Bob:
white,
Claire:
pink.
\n
(2)
Bob
and
Claire
swap
balls:
Alice:
purple,
Bob:
pink,
Claire:
white.
\n
(3)
Bob
and
Alice
swap
balls:
Alice:
pink,
Bob:
purple,
Claire:
white.
\n
At
the
end
of
the
game,
Alice
has
the
pink
ball.
So
the
answer
is
(C).
\n\n
Q:
Alice,
Bob,
and
Claire
are
dancers
at
a
square
dance.
At
the
start
of
a
song,
they
each
have
a
partner:
Alice
is
dancing
with
Lola,
Bob
is
dancing
with
Rodrigo,
and
Claire
is
dancing
with
Patrick.
\n
Throughout
the
song,
the
dancers
often
trade
partners.
First,
Alice
and
Bob
switch
partners.
Then,
Claire
and
Bob
switch
partners.
Finally,
Bob
and
Alice
switch
partners.
At
the
end
of
the
dance,
Alice
is
dancing
with
\n
Options:
\n
(A)
Lola
\n
(B)
Rodrigo
\n
(C)
Patrick
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
Lola,
Bob:
Rodrigo,
Claire:
Patrick.
\n
(1)
Alice
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Lola,
Claire:
Patrick.
\n
(2)
Claire
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Patrick,
Claire:
Lola.
\n
(3)
Bob
and
Alice
switch
partners:
Alice:
Patrick,
Bob:
Rodrigo,
Claire:
Lola.
\n
At
the
end
of
the
dance,
Alice
is
dancing
with
Patrick.
So
the
answer
is
(C).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step.
\n
"
"
doc_to_text"
:
"
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
yellow
ball,
Bob
has
a
blue
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Claire
and
Alice
swap
balls.
Then,
Alice
and
Bob
swap
balls.
Finally,
Claire
and
Bob
swap
balls.
At
the
end
of
the
game,
Bob
has
the
\n
Options:
\n
(A)
yellow
ball
\n
(B)
blue
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
yellow,
Bob:
blue,
Claire:
pink.
\n
(1)
Claire
and
Alice
swap
balls:
Alice:
pink,
Bob:
blue,
Claire:
yellow.
\n
(2)
Alice
and
Bob
swap
balls:
Alice:
blue,
Bob:
pink,
Claire:
yellow.
\n
(3)
Claire
and
Bob
swap
balls:
Alice:
blue,
Bob:
yellow,
Claire:
pink.
\n
At
the
end
of
the
game,
Bob
has
the
yellow
ball.
So
the
answer
is
(A).
\n\n
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
white
ball,
Bob
has
a
purple
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Bob
and
Alice
swap
balls.
Then,
Bob
and
Claire
swap
balls.
Finally,
Bob
and
Alice
swap
balls.
At
the
end
of
the
game,
Alice
has
the
\n
Options:
\n
(A)
white
ball
\n
(B)
purple
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
white,
Bob:
purple,
Claire:
pink.
\n
(1)
Bob
and
Alice
swap
balls:
Alice:
purple,
Bob:
white,
Claire:
pink.
\n
(2)
Bob
and
Claire
swap
balls:
Alice:
purple,
Bob:
pink,
Claire:
white.
\n
(3)
Bob
and
Alice
swap
balls:
Alice:
pink,
Bob:
purple,
Claire:
white.
\n
At
the
end
of
the
game,
Alice
has
the
pink
ball.
So
the
answer
is
(C).
\n\n
Q:
Alice,
Bob,
and
Claire
are
dancers
at
a
square
dance.
At
the
start
of
a
song,
they
each
have
a
partner:
Alice
is
dancing
with
Lola,
Bob
is
dancing
with
Rodrigo,
and
Claire
is
dancing
with
Patrick.
\n
Throughout
the
song,
the
dancers
often
trade
partners.
First,
Alice
and
Bob
switch
partners.
Then,
Claire
and
Bob
switch
partners.
Finally,
Bob
and
Alice
switch
partners.
At
the
end
of
the
dance,
Alice
is
dancing
with
\n
Options:
\n
(A)
Lola
\n
(B)
Rodrigo
\n
(C)
Patrick
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
Lola,
Bob:
Rodrigo,
Claire:
Patrick.
\n
(1)
Alice
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Lola,
Claire:
Patrick.
\n
(2)
Claire
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Patrick,
Claire:
Lola.
\n
(3)
Bob
and
Alice
switch
partners:
Alice:
Patrick,
Bob:
Rodrigo,
Claire:
Lola.
\n
At
the
end
of
the
dance,
Alice
is
dancing
with
Patrick.
So
the
answer
is
(C).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step."
"
include"
:
"
_cot_fewshot_template_yaml"
"
include"
:
"
_cot_fewshot_template_yaml"
"
task"
:
"
bbh_cot_fewshot_tracking_shuffled_objects_seven_objects"
"
task"
:
"
bbh_cot_fewshot_tracking_shuffled_objects_seven_objects"
filter_list
:
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
-1
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
-
name
:
"
strict-match"
filter
:
-
function
:
"
regex"
regex_pattern
:
"
((?<=The
answer
is
)(.*)(?=.)|(?<=the
answer
is
)(.*)(?=.)|(?<=The
answer:
)(.*)(?=.)|(?<=The
final
answer:
)(.*)(?=.))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/cot_fewshot/tracking_shuffled_objects_three_objects.yaml
View file @
e2909b33
"
dataset_name"
:
"
tracking_shuffled_objects_three_objects"
"
dataset_name"
:
"
tracking_shuffled_objects_three_objects"
"
description"
:
"
A
task
requiring
determining
the
final
positions
of
a
set
of
objects
given
their
initial
positions
and
a
description
of
a
sequence
of
swaps.
\n\n
"
"
description"
:
"
A
task
requiring
determining
the
final
positions
of
a
set
of
objects
given
their
initial
positions
and
a
description
of
a
sequence
of
swaps.
\n\n
"
"
doc_to_text"
:
"
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
yellow
ball,
Bob
has
a
blue
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Claire
and
Alice
swap
balls.
Then,
Alice
and
Bob
swap
balls.
Finally,
Claire
and
Bob
swap
balls.
At
the
end
of
the
game,
Bob
has
the
\n
Options:
\n
(A)
yellow
ball
\n
(B)
blue
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
yellow,
Bob:
blue,
Claire:
pink.
\n
(1)
Claire
and
Alice
swap
balls:
Alice:
pink,
Bob:
blue,
Claire:
yellow.
\n
(2)
Alice
and
Bob
swap
balls:
Alice:
blue,
Bob:
pink,
Claire:
yellow.
\n
(3)
Claire
and
Bob
swap
balls:
Alice:
blue,
Bob:
yellow,
Claire:
pink.
\n
At
the
end
of
the
game,
Bob
has
the
yellow
ball.
So
the
answer
is
(A).
\n\n
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
white
ball,
Bob
has
a
purple
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Bob
and
Alice
swap
balls.
Then,
Bob
and
Claire
swap
balls.
Finally,
Bob
and
Alice
swap
balls.
At
the
end
of
the
game,
Alice
has
the
\n
Options:
\n
(A)
white
ball
\n
(B)
purple
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
white,
Bob:
purple,
Claire:
pink.
\n
(1)
Bob
and
Alice
swap
balls:
Alice:
purple,
Bob:
white,
Claire:
pink.
\n
(2)
Bob
and
Claire
swap
balls:
Alice:
purple,
Bob:
pink,
Claire:
white.
\n
(3)
Bob
and
Alice
swap
balls:
Alice:
pink,
Bob:
purple,
Claire:
white.
\n
At
the
end
of
the
game,
Alice
has
the
pink
ball.
So
the
answer
is
(C).
\n\n
Q:
Alice,
Bob,
and
Claire
are
dancers
at
a
square
dance.
At
the
start
of
a
song,
they
each
have
a
partner:
Alice
is
dancing
with
Lola,
Bob
is
dancing
with
Rodrigo,
and
Claire
is
dancing
with
Patrick.
\n
Throughout
the
song,
the
dancers
often
trade
partners.
First,
Alice
and
Bob
switch
partners.
Then,
Claire
and
Bob
switch
partners.
Finally,
Bob
and
Alice
switch
partners.
At
the
end
of
the
dance,
Alice
is
dancing
with
\n
Options:
\n
(A)
Lola
\n
(B)
Rodrigo
\n
(C)
Patrick
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
Lola,
Bob:
Rodrigo,
Claire:
Patrick.
\n
(1)
Alice
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Lola,
Claire:
Patrick.
\n
(2)
Claire
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Patrick,
Claire:
Lola.
\n
(3)
Bob
and
Alice
switch
partners:
Alice:
Patrick,
Bob:
Rodrigo,
Claire:
Lola.
\n
At
the
end
of
the
dance,
Alice
is
dancing
with
Patrick.
So
the
answer
is
(C).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step.
\n
"
"
doc_to_text"
:
"
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
yellow
ball,
Bob
has
a
blue
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Claire
and
Alice
swap
balls.
Then,
Alice
and
Bob
swap
balls.
Finally,
Claire
and
Bob
swap
balls.
At
the
end
of
the
game,
Bob
has
the
\n
Options:
\n
(A)
yellow
ball
\n
(B)
blue
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
yellow,
Bob:
blue,
Claire:
pink.
\n
(1)
Claire
and
Alice
swap
balls:
Alice:
pink,
Bob:
blue,
Claire:
yellow.
\n
(2)
Alice
and
Bob
swap
balls:
Alice:
blue,
Bob:
pink,
Claire:
yellow.
\n
(3)
Claire
and
Bob
swap
balls:
Alice:
blue,
Bob:
yellow,
Claire:
pink.
\n
At
the
end
of
the
game,
Bob
has
the
yellow
ball.
So
the
answer
is
(A).
\n\n
Q:
Alice,
Bob,
and
Claire
are
playing
a
game.
At
the
start
of
the
game,
they
are
each
holding
a
ball:
Alice
has
a
white
ball,
Bob
has
a
purple
ball,
and
Claire
has
a
pink
ball.
\n
As
the
game
progresses,
pairs
of
players
trade
balls.
First,
Bob
and
Alice
swap
balls.
Then,
Bob
and
Claire
swap
balls.
Finally,
Bob
and
Alice
swap
balls.
At
the
end
of
the
game,
Alice
has
the
\n
Options:
\n
(A)
white
ball
\n
(B)
purple
ball
\n
(C)
pink
ball
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
white,
Bob:
purple,
Claire:
pink.
\n
(1)
Bob
and
Alice
swap
balls:
Alice:
purple,
Bob:
white,
Claire:
pink.
\n
(2)
Bob
and
Claire
swap
balls:
Alice:
purple,
Bob:
pink,
Claire:
white.
\n
(3)
Bob
and
Alice
swap
balls:
Alice:
pink,
Bob:
purple,
Claire:
white.
\n
At
the
end
of
the
game,
Alice
has
the
pink
ball.
So
the
answer
is
(C).
\n\n
Q:
Alice,
Bob,
and
Claire
are
dancers
at
a
square
dance.
At
the
start
of
a
song,
they
each
have
a
partner:
Alice
is
dancing
with
Lola,
Bob
is
dancing
with
Rodrigo,
and
Claire
is
dancing
with
Patrick.
\n
Throughout
the
song,
the
dancers
often
trade
partners.
First,
Alice
and
Bob
switch
partners.
Then,
Claire
and
Bob
switch
partners.
Finally,
Bob
and
Alice
switch
partners.
At
the
end
of
the
dance,
Alice
is
dancing
with
\n
Options:
\n
(A)
Lola
\n
(B)
Rodrigo
\n
(C)
Patrick
\n
A:
Let's
think
step
by
step.
\n
(0)
At
the
start:
Alice:
Lola,
Bob:
Rodrigo,
Claire:
Patrick.
\n
(1)
Alice
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Lola,
Claire:
Patrick.
\n
(2)
Claire
and
Bob
switch
partners:
Alice:
Rodrigo,
Bob:
Patrick,
Claire:
Lola.
\n
(3)
Bob
and
Alice
switch
partners:
Alice:
Patrick,
Bob:
Rodrigo,
Claire:
Lola.
\n
At
the
end
of
the
dance,
Alice
is
dancing
with
Patrick.
So
the
answer
is
(C).
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step."
"
include"
:
"
_cot_fewshot_template_yaml"
"
include"
:
"
_cot_fewshot_template_yaml"
"
task"
:
"
bbh_cot_fewshot_tracking_shuffled_objects_three_objects"
"
task"
:
"
bbh_cot_fewshot_tracking_shuffled_objects_three_objects"
filter_list
:
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
-1
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
-
name
:
"
strict-match"
filter
:
-
function
:
"
regex"
regex_pattern
:
"
((?<=The
answer
is
)(.*)(?=.)|(?<=the
answer
is
)(.*)(?=.)|(?<=The
answer:
)(.*)(?=.)|(?<=The
final
answer:
)(.*)(?=.))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/cot_fewshot/utils.py
0 → 100644
View file @
e2909b33
import
collections
import
re
import
sys
import
unicodedata
from
lm_eval.filters.extraction
import
Filter
,
RegexFilter
class
ExtendedRegexFilter
(
RegexFilter
):
punct_tbl
=
dict
.
fromkeys
(
i
for
i
in
range
(
sys
.
maxunicode
)
if
unicodedata
.
category
(
chr
(
i
)).
startswith
(
"P"
)
)
def
__init__
(
self
,
regex_pattern
:
str
=
r
"#### (\-?[0-9\.\,]+)"
,
group_select
=
0
,
fallback
:
str
=
"[invalid]"
,
ignore_case
=
False
,
ignore_punctuation
=
False
,
regexes_to_ignore
=
None
,
)
->
None
:
super
().
__init__
(
regex_pattern
,
group_select
,
fallback
)
self
.
ignore_case
=
ignore_case
self
.
ignore_punctuation
=
ignore_punctuation
self
.
regexes_to_ignore
=
regexes_to_ignore
def
filter_ignores
(
self
,
st
):
if
self
.
regexes_to_ignore
is
not
None
:
for
s
in
self
.
regexes_to_ignore
:
st
=
re
.
sub
(
s
,
""
,
st
)
if
self
.
ignore_case
:
st
=
st
.
lower
()
if
self
.
ignore_punctuation
:
# https://stackoverflow.com/a/266162
st
=
st
.
translate
(
self
.
punct_tbl
)
return
st
def
find_match
(
self
,
regex
,
resp
,
convert_dict
=
{}):
match
=
regex
.
findall
(
resp
)
if
match
:
match
=
match
[
self
.
group_select
]
if
isinstance
(
match
,
tuple
):
match
=
[
m
for
m
in
match
if
m
][
0
]
match
=
match
.
strip
()
if
match
and
match
in
convert_dict
:
match
=
convert_dict
[
match
]
return
match
class
MapRegexFilter
(
ExtendedRegexFilter
):
def
__init__
(
self
,
regex_pattern_to_value
:
dict
=
{},
group_select
=
0
,
fallback
:
str
=
"[invalid]"
,
ignore_case
=
False
,
ignore_punctuation
=
False
,
regexes_to_ignore
=
None
,
)
->
None
:
"""
regex_pattern_to_value: Match the regex pattern and change the result into the value
group_select: Selects the (group_select)th match from the findall result. We use the whole regex_patterns, concatenated by |
ignore_case: Lowers the case of response before matching with the given regex
ignore_punctuation: Remove the punctuation before matching with the given regex
regexes_to_ignore: Remove these regexes before matching with the given regex
"""
super
().
__init__
(
"|"
.
join
(
list
(
regex_pattern_to_value
.
keys
())),
group_select
,
fallback
,
ignore_case
,
ignore_punctuation
,
regexes_to_ignore
,
)
self
.
regex_to_value
=
{
re
.
compile
(
r
):
v
for
r
,
v
in
regex_pattern_to_value
.
items
()
}
def
apply
(
self
,
resps
,
docs
):
filtered_resps
=
[]
for
r
in
resps
:
filtered
=
[]
for
resp
in
r
:
whole_match_considering_group_select
=
self
.
find_match
(
self
.
regex
,
self
.
filter_ignores
(
resp
)
)
if
whole_match_considering_group_select
:
for
regex
,
mapped_value
in
self
.
regex_to_value
.
items
():
match
=
self
.
find_match
(
regex
,
self
.
filter_ignores
(
whole_match_considering_group_select
),
)
if
match
:
match
=
mapped_value
break
if
not
whole_match_considering_group_select
or
not
match
:
match
=
self
.
fallback
filtered
.
append
(
match
)
filtered_resps
.
append
(
filtered
)
return
filtered_resps
class
NumberParseRegexFilter
(
ExtendedRegexFilter
):
def
apply
(
self
,
resps
,
docs
):
# here, we assume we have a list, in which each element is
# a list of model responses for some particular input/target pair.
# so we process each of these (same input/target response sets)
# independently (and keep them a list.)
filtered_resps
=
[]
import
regex
from
word2number
import
w2n
# https://www.reddit.com/r/regex/comments/11a38uk/parsing_numbers_written_out_as_english_words
english_number_regex
=
regex
.
compile
(
"((?:(?:zero|one|two|three|four|five|(?:twen|thir|for|fif|six|seven|nine)(?|teen|ty)|eight(?:|een|y)|ten|eleven|twelve|fourteen|hundred|thousand|(?:m|b|tr)illion)(?:zero|one|two|three|four|five|(?:twen|thir|for|fif|six|seven|nine)(?:|teen|ty)|eight(?|een|y)|ten|eleven|twelve|fourteen|hundred|thousand|(?:m|b|tr)illion|[^\S
\r\n
]|,|and|&)+)?(?:zero|one|two|three|four|five|(?:twen|thir|for|fif|six|seven|nine)(?|teen|ty)|eight(?|een|y)|ten|eleven|twelve|fourteen|hundred|thousand|(?:m|b|tr)illion))"
)
for
r
in
resps
:
filtered
=
[]
for
resp
in
r
:
match
=
self
.
find_match
(
self
.
regex
,
resp
)
if
not
match
:
match
=
self
.
find_match
(
english_number_regex
,
resp
.
lower
())
if
match
:
match
=
str
(
w2n
.
word_to_num
(
match
))
if
not
match
:
match
=
self
.
fallback
filtered
.
append
(
match
)
filtered_resps
.
append
(
filtered
)
return
filtered_resps
class
WordSortFilter
(
Filter
):
""" """
def
apply
(
self
,
resps
,
docs
):
filtered_resps
=
[]
for
r
,
doc
in
zip
(
resps
,
docs
):
words
=
doc
[
"input"
].
split
(
"List:"
)[
1
].
strip
().
split
()
regex
=
re
.
compile
(
"|"
.
join
([
f
"
\\
b
{
w
}
\\
b"
for
w
in
words
]))
filtered
=
[]
for
resp
in
r
:
match
=
regex
.
findall
(
resp
)
match
.
reverse
()
ordered_words
=
reversed
(
collections
.
OrderedDict
(
zip
(
match
,
[
None
]
*
len
(
match
)))
)
filtered
.
append
(
" "
.
join
(
ordered_words
))
filtered_resps
.
append
(
filtered
)
return
filtered_resps
class
MultiChoiceRegexFilter
(
ExtendedRegexFilter
):
def
__init__
(
self
,
*
args
,
**
kwargs
):
"""
regex_pattern: The basic regex pattern to use. If fails to match, we will use the customized match procedure
- step 1 : We parse the choices between ([A-Z])s then try to find these choices in the response.
- step 2 : We parse the choice with regex :[\s]*([A-?]), where ? varies by number of choices.
group_select: Selects the (group_select)th match from the findall result.
ignore_case: Ignores the case during step 1 matching
ignore_punctuation: Remove the punctuation during step 1 matching
regexes_to_ignore: Remove these regexes during step 1 matching
"""
super
().
__init__
(
*
args
,
**
kwargs
)
def
apply
(
self
,
resps
,
docs
):
# here, we assume we have a list, in which each element is
# a list of model responses for some particular input/target pair.
# so we process each of these (same input/target response sets)
# independently (and keep them a list.)
filtered_resps
=
[]
for
r
,
doc
in
zip
(
resps
,
docs
):
fallback_regexes
=
[]
choice_to_alpha
=
{}
next_alpha
=
"A"
without_paren_fallback_regexes
=
[]
without_paren_to_target
=
{}
multiple_choices_regex
=
re
.
compile
(
r
"\([A-Z]\)([^\n^(]*)"
)
match
=
multiple_choices_regex
.
findall
(
doc
[
"input"
])
for
m
in
match
:
m
=
self
.
filter_ignores
(
m
.
strip
())
fallback_regexes
.
append
(
f
"
{
re
.
escape
(
m
)
}
"
)
choice_to_alpha
[
m
]
=
f
"(
{
next_alpha
}
)"
without_paren_fallback_regexes
.
append
(
next_alpha
)
without_paren_to_target
[
next_alpha
]
=
f
"(
{
next_alpha
}
)"
next_alpha
=
chr
(
ord
(
next_alpha
)
+
1
)
fallback_regex
=
re
.
compile
(
"|"
.
join
(
fallback_regexes
))
without_paren_fallback_regex
=
"|"
.
join
(
without_paren_fallback_regexes
)
without_paren_fallback_regex
=
re
.
compile
(
f
":[\s]*(
{
without_paren_fallback_regex
}
)"
)
filtered
=
[]
for
resp
in
r
:
match
=
self
.
find_match
(
self
.
regex
,
resp
)
if
not
match
:
match
=
self
.
find_match
(
fallback_regex
,
self
.
filter_ignores
(
resp
),
choice_to_alpha
)
if
not
match
:
match
=
self
.
find_match
(
without_paren_fallback_regex
,
resp
,
without_paren_to_target
)
if
not
match
:
match
=
self
.
fallback
filtered
.
append
(
match
)
filtered_resps
.
append
(
filtered
)
return
filtered_resps
lm_eval/tasks/bbh/cot_fewshot/web_of_lies.yaml
View file @
e2909b33
"
dataset_name"
:
"
web_of_lies"
"
dataset_name"
:
"
web_of_lies"
"
description"
:
"
Evaluate
a
random
boolean
function
expressed
as
a
word
problem.
\n\n
"
"
description"
:
"
Evaluate
a
random
boolean
function
expressed
as
a
word
problem.
\n\n
"
"
doc_to_text"
:
"
Q:
Question:
Fidel
tells
the
truth.
Jerry
says
Fidel
tells
the
truth.
Vina
says
Jerry
tells
the
truth.
Millicent
says
Vina
lies.
Raymond
says
Millicent
lies.
Does
Raymond
tell
the
truth?
\n
A:
Let's
think
step
by
step.
\n
(1)
Fidel
tells
the
truth.
So,
we
know
that
Fidel
tells
the
truth.
\n
(2)
Jerry
says
Fidel
tells
the
truth.
Since
we
know
from
(1)
that
Fidel
tells
the
truth,
if
Jerry
says
that
Fidel
tells
the
truth,
then
Jerry
tells
the
truth.
\n
(3)
Vina
says
Jerry
tells
the
truth.
Since
we
know
from
(2)
that
Jerry
tells
the
truth,
if
Vina
says
Jerry
tells
the
truth,
then
Vine
tells
the
truth.
\n
(4)
Millicent
says
Vina
lies.
Since
we
know
from
(3)
that
Vina
tells
the
truth,
if
Millicent
says
Vina
lies,
then
Millicent
lies.
\n
(5)
Raymond
says
Millicent
lies.
Since
we
know
from
(4)
that
Millicent
lies,
if
Raymond
says
Millicent
lies,
then
Raymond
tells
the
truth.
\n
Now,
the
question
asks:
Does
Raymond
tell
the
truth?
We
know
from
(5)
that
Raymond
tells
the
truth.
So
the
answer
is
Yes.
\n\n
Q:
Question:
Kristian
lies.
Millie
says
Kristian
lies.
Maybelle
says
Millie
tells
the
truth.
Fidel
says
Maybelle
lies.
Leda
says
Fidel
lies.
Does
Leda
tell
the
truth?
\n
A:
Let's
think
step
by
step.
\n
(1)
Kristian
lies.
So,
we
know
that
Kristian
lies.
\n
(2)
Millie
says
Kristian
lies.
Since
we
know
from
(1)
that
Kristian
lies,
if
Millie
says
Kristian
lies,
then
Millie
tells
the
truth.
\n
(3)
Maybelle
says
Millie
tells
the
truth.
Since
we
know
from
(2)
that
Millie
tells
the
truth,
if
Maybelle
says
Millie
tells
the
truth,
then
Maybelle
tells
the
truth.
\n
(4)
Fidel
says
Maybelle
lies.
Since
we
know
from
(3)
that
Maybelle
tells
the
truth,
if
Fidel
says
Maybelle
lies,
then
Fidel
lies.
\n
(5)
Leda
says
Fidel
lies.
Since
we
know
from
(4)
that
Fidel
lies,
if
Leda
says
Fidel
lies,
then
Leda
tells
the
truth.
\n
Now,
the
question
asks:
Does
Leda
tell
the
truth?
We
know
from
(5)
that
Leda
tells
the
truth.
So
the
answer
is
Yes.
\n\n
Q:
Question:
Kristian
tells
the
truth.
Michaela
says
Kristian
lies.
Raymond
says
Michaela
tells
the
truth.
Osvaldo
says
Raymond
tells
the
truth.
Jamey
says
Osvaldo
tells
the
truth.
Does
Jamey
tell
the
truth?
\n
A:
Let's
think
step
by
step.
\n
(1)
Kristian
tells
the
truth.
So,
we
know
that
Kristian
tells
the
truth.
\n
(2)
Michaela
says
Kristian
lies.
Since
we
know
from
(1)
that
Kristian
tells
the
truth,
if
Michaela
says
Kristian
lies,
then
Michaela
lies.
\n
(3)
Raymond
says
Michaela
tells
the
truth.
Since
we
know
from
(2)
that
Michaela
lies,
if
Raymond
says
Michaela
tells
the
truth,
then
Raymond
lies.
\n
(4)
Osvaldo
says
Raymond
tells
the
truth.
Since
we
know
from
(3)
that
Raymond
lies,
if
Osvaldo
says
Raymond
tells
the
truth,
then
Osvaldo
lies.
\n
(5)
Jamey
says
Osvaldo
tells
the
truth.
Since
we
know
from
(4)
that
Osvaldo
lies,
if
Jamey
says
Osvaldo
tells
the
truth,
then
Jamey
lies.
\n
Now,
the
question
asks:
Does
Jamey
tell
the
truth?
We
know
from
(5)
that
Jamey
lies.
So
the
answer
is
No.
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step.
\n
"
"
doc_to_text"
:
"
Q:
Question:
Fidel
tells
the
truth.
Jerry
says
Fidel
tells
the
truth.
Vina
says
Jerry
tells
the
truth.
Millicent
says
Vina
lies.
Raymond
says
Millicent
lies.
Does
Raymond
tell
the
truth?
\n
A:
Let's
think
step
by
step.
\n
(1)
Fidel
tells
the
truth.
So,
we
know
that
Fidel
tells
the
truth.
\n
(2)
Jerry
says
Fidel
tells
the
truth.
Since
we
know
from
(1)
that
Fidel
tells
the
truth,
if
Jerry
says
that
Fidel
tells
the
truth,
then
Jerry
tells
the
truth.
\n
(3)
Vina
says
Jerry
tells
the
truth.
Since
we
know
from
(2)
that
Jerry
tells
the
truth,
if
Vina
says
Jerry
tells
the
truth,
then
Vine
tells
the
truth.
\n
(4)
Millicent
says
Vina
lies.
Since
we
know
from
(3)
that
Vina
tells
the
truth,
if
Millicent
says
Vina
lies,
then
Millicent
lies.
\n
(5)
Raymond
says
Millicent
lies.
Since
we
know
from
(4)
that
Millicent
lies,
if
Raymond
says
Millicent
lies,
then
Raymond
tells
the
truth.
\n
Now,
the
question
asks:
Does
Raymond
tell
the
truth?
We
know
from
(5)
that
Raymond
tells
the
truth.
So
the
answer
is
Yes.
\n\n
Q:
Question:
Kristian
lies.
Millie
says
Kristian
lies.
Maybelle
says
Millie
tells
the
truth.
Fidel
says
Maybelle
lies.
Leda
says
Fidel
lies.
Does
Leda
tell
the
truth?
\n
A:
Let's
think
step
by
step.
\n
(1)
Kristian
lies.
So,
we
know
that
Kristian
lies.
\n
(2)
Millie
says
Kristian
lies.
Since
we
know
from
(1)
that
Kristian
lies,
if
Millie
says
Kristian
lies,
then
Millie
tells
the
truth.
\n
(3)
Maybelle
says
Millie
tells
the
truth.
Since
we
know
from
(2)
that
Millie
tells
the
truth,
if
Maybelle
says
Millie
tells
the
truth,
then
Maybelle
tells
the
truth.
\n
(4)
Fidel
says
Maybelle
lies.
Since
we
know
from
(3)
that
Maybelle
tells
the
truth,
if
Fidel
says
Maybelle
lies,
then
Fidel
lies.
\n
(5)
Leda
says
Fidel
lies.
Since
we
know
from
(4)
that
Fidel
lies,
if
Leda
says
Fidel
lies,
then
Leda
tells
the
truth.
\n
Now,
the
question
asks:
Does
Leda
tell
the
truth?
We
know
from
(5)
that
Leda
tells
the
truth.
So
the
answer
is
Yes.
\n\n
Q:
Question:
Kristian
tells
the
truth.
Michaela
says
Kristian
lies.
Raymond
says
Michaela
tells
the
truth.
Osvaldo
says
Raymond
tells
the
truth.
Jamey
says
Osvaldo
tells
the
truth.
Does
Jamey
tell
the
truth?
\n
A:
Let's
think
step
by
step.
\n
(1)
Kristian
tells
the
truth.
So,
we
know
that
Kristian
tells
the
truth.
\n
(2)
Michaela
says
Kristian
lies.
Since
we
know
from
(1)
that
Kristian
tells
the
truth,
if
Michaela
says
Kristian
lies,
then
Michaela
lies.
\n
(3)
Raymond
says
Michaela
tells
the
truth.
Since
we
know
from
(2)
that
Michaela
lies,
if
Raymond
says
Michaela
tells
the
truth,
then
Raymond
lies.
\n
(4)
Osvaldo
says
Raymond
tells
the
truth.
Since
we
know
from
(3)
that
Raymond
lies,
if
Osvaldo
says
Raymond
tells
the
truth,
then
Osvaldo
lies.
\n
(5)
Jamey
says
Osvaldo
tells
the
truth.
Since
we
know
from
(4)
that
Osvaldo
lies,
if
Jamey
says
Osvaldo
tells
the
truth,
then
Jamey
lies.
\n
Now,
the
question
asks:
Does
Jamey
tell
the
truth?
We
know
from
(5)
that
Jamey
lies.
So
the
answer
is
No.
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step."
"
include"
:
"
_cot_fewshot_template_yaml"
"
include"
:
"
_cot_fewshot_template_yaml"
"
task"
:
"
bbh_cot_fewshot_web_of_lies"
"
task"
:
"
bbh_cot_fewshot_web_of_lies"
filter_list
:
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MapRegexFilter
group_select
:
-1
ignore_case
:
true
regex_pattern_to_value
:
\b(no|does not tell the truth|is not telling the truth)\b
:
"
no"
\b(yes|tells the truth|is telling the truth)\b
:
"
yes"
-
function
:
"
take_first"
-
name
:
"
strict-match"
filter
:
-
function
:
"
regex"
regex_pattern
:
"
((?<=The
answer
is
)(.*)(?=.)|(?<=the
answer
is
)(.*)(?=.)|(?<=The
answer:
)(.*)(?=.)|(?<=The
final
answer:
)(.*)(?=.))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/cot_fewshot/word_sorting.yaml
View file @
e2909b33
"
dataset_name"
:
"
word_sorting"
"
dataset_name"
:
"
word_sorting"
"
description"
:
"
Sort
a
list
of
words.
\n\n
"
"
description"
:
"
Sort
a
list
of
words.
\n\n
"
"
doc_to_text"
:
"
Q:
Sort
the
following
words
alphabetically:
List:
oven
costume
counterpart
\n
A:
Let's
think
step
by
step.
\n
The
first
letter:
\"
oven
\"
:
\"
o
\"
(15).
\"
costume
\"
:
\"
c
\"
(3).
\"
counterpart
\"
:
\"
c
\"
(3).
We
now
have:
(3)
[
\"
costume
\"
?
\"
counterpart
\"
]
<
(15)
\"
oven
\"
.
Now
let's
sort
this
subpart
[
\"
costume
\"
?
\"
counterpart
\"
]
by
looking
at
their
second
letters.
\n
The
second
letter:
\"
costume
\"
:
\"
o
\"
(15).
\"
counterpart
\"
:
\"
o
\"
(15).
We
now
have:
(15)
[
\"
costume
\"
?
\"
counterpart
\"
].
Now
let's
sort
this
subpart
[
\"
costume
\"
?
\"
counterpart
\"
]
by
looking
at
their
third
letters.
\n
The
third
letter:
\"
costume
\"
:
\"
s
\"
(19).
\"
counterpart
\"
:
\"
u
\"
(21).
We
now
have:
(19)
\"
costume
\"
<
(21)
\"
counterpart
\"
.
Hence,
we
have
[
\"
costume
\"
<
\"
counterpart
\"
]
<
\"
oven
\"
.
So
the
answer
is
costume
counterpart
oven.
\n\n
Q:
Sort
the
following
words
alphabetically:
List:
hypochlorite
ponderosa
phone
credulity
\n
A:
Let's
think
step
by
step.
\n
The
first
letter:
\"
hypochlorite
\"
:
\"
h
\"
(8).
\"
ponderosa
\"
:
\"
p
\"
(16).
\"
phone
\"
:
\"
p
\"
(16).
\"
credulity
\"
:
\"
c
\"
(3).
We
now
have:
(3)
\"
credulity
\"
<
(8)
\"
hypochlorite
\"
<
(16)
[
\"
ponderosa
\"
?
\"
phone
\"
].
Now
let's
sort
this
subpart
[
\"
ponderosa
\"
?
\"
phone
\"
]
by
looking
at
their
second
letters.
\n
The
second
letter:
\"
ponderosa
\"
:
\"
o
\"
(15).
\"
phone
\"
:
\"
h
\"
(8).
We
now
have:
(8)
\"
phone
\"
<
(15)
\"
ponderosa
\"
.
Hence,
we
have
\"
credulity
\"
<
\"
hypochlorite
\"
<
[
\"
phone
\"
<
\"
ponderosa
\"
].
So
the
answer
is
credulity
hypochlorite
phone
ponderosa.
\n\n
Q:
Sort
the
following
words
alphabetically:
List:
newt
arson
parthia
seismography
mugho
aspect
census
\n
A:
Let's
think
step
by
step.
\n
The
first
letter:
\"
newt
\"
:
\"
n
\"
(14).
\"
arson
\"
:
\"
a
\"
(1).
\"
parthia
\"
:
\"
p
\"
(16).
\"
seismography
\"
:
\"
s
\"
(19).
\"
mugho
\"
:
\"
m
\"
(13).
\"
aspect
\"
:
\"
a
\"
(1).
\"
census
\"
:
\"
c
\"
(3).
We
now
have:
(1)
[
\"
arson
\"
?
\"
aspect
\"
]
<
(3)
\"
census
\"
<
(13)
\"
mugho
\"
<
(14)
\"
newt
\"
<
(16)
\"
parthia
\"
<
(19)
\"
seismography
\"
.
Now
let's
sort
this
subpart
[
\"
arson
\"
?
\"
aspect
\"
]
by
looking
at
their
second
letters.
\n
The
second
letter:
\"
arson
\"
:
\"
r
\"
(18).
\"
aspect
\"
:
\"
s
\"
(19).
We
now
have:
(18)
\"
arson
\"
<
(19)
\"
aspect
\"
.
Hence,
we
have
[
\"
arson
\"
<
\"
aspect
\"
]
<
\"
census
\"
<
\"
mugho
\"
<
\"
newt
\"
<
\"
parthia
\"
<
\"
seismography
\"
.
So
the
answer
is
arson
aspect
census
mugho
newt
parthia
seismography.
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step.
\n
"
"
doc_to_text"
:
"
Q:
Sort
the
following
words
alphabetically:
List:
oven
costume
counterpart
\n
A:
Let's
think
step
by
step.
\n
The
first
letter:
\"
oven
\"
:
\"
o
\"
(15).
\"
costume
\"
:
\"
c
\"
(3).
\"
counterpart
\"
:
\"
c
\"
(3).
We
now
have:
(3)
[
\"
costume
\"
?
\"
counterpart
\"
]
<
(15)
\"
oven
\"
.
Now
let's
sort
this
subpart
[
\"
costume
\"
?
\"
counterpart
\"
]
by
looking
at
their
second
letters.
\n
The
second
letter:
\"
costume
\"
:
\"
o
\"
(15).
\"
counterpart
\"
:
\"
o
\"
(15).
We
now
have:
(15)
[
\"
costume
\"
?
\"
counterpart
\"
].
Now
let's
sort
this
subpart
[
\"
costume
\"
?
\"
counterpart
\"
]
by
looking
at
their
third
letters.
\n
The
third
letter:
\"
costume
\"
:
\"
s
\"
(19).
\"
counterpart
\"
:
\"
u
\"
(21).
We
now
have:
(19)
\"
costume
\"
<
(21)
\"
counterpart
\"
.
Hence,
we
have
[
\"
costume
\"
<
\"
counterpart
\"
]
<
\"
oven
\"
.
So
the
answer
is
costume
counterpart
oven.
\n\n
Q:
Sort
the
following
words
alphabetically:
List:
hypochlorite
ponderosa
phone
credulity
\n
A:
Let's
think
step
by
step.
\n
The
first
letter:
\"
hypochlorite
\"
:
\"
h
\"
(8).
\"
ponderosa
\"
:
\"
p
\"
(16).
\"
phone
\"
:
\"
p
\"
(16).
\"
credulity
\"
:
\"
c
\"
(3).
We
now
have:
(3)
\"
credulity
\"
<
(8)
\"
hypochlorite
\"
<
(16)
[
\"
ponderosa
\"
?
\"
phone
\"
].
Now
let's
sort
this
subpart
[
\"
ponderosa
\"
?
\"
phone
\"
]
by
looking
at
their
second
letters.
\n
The
second
letter:
\"
ponderosa
\"
:
\"
o
\"
(15).
\"
phone
\"
:
\"
h
\"
(8).
We
now
have:
(8)
\"
phone
\"
<
(15)
\"
ponderosa
\"
.
Hence,
we
have
\"
credulity
\"
<
\"
hypochlorite
\"
<
[
\"
phone
\"
<
\"
ponderosa
\"
].
So
the
answer
is
credulity
hypochlorite
phone
ponderosa.
\n\n
Q:
Sort
the
following
words
alphabetically:
List:
newt
arson
parthia
seismography
mugho
aspect
census
\n
A:
Let's
think
step
by
step.
\n
The
first
letter:
\"
newt
\"
:
\"
n
\"
(14).
\"
arson
\"
:
\"
a
\"
(1).
\"
parthia
\"
:
\"
p
\"
(16).
\"
seismography
\"
:
\"
s
\"
(19).
\"
mugho
\"
:
\"
m
\"
(13).
\"
aspect
\"
:
\"
a
\"
(1).
\"
census
\"
:
\"
c
\"
(3).
We
now
have:
(1)
[
\"
arson
\"
?
\"
aspect
\"
]
<
(3)
\"
census
\"
<
(13)
\"
mugho
\"
<
(14)
\"
newt
\"
<
(16)
\"
parthia
\"
<
(19)
\"
seismography
\"
.
Now
let's
sort
this
subpart
[
\"
arson
\"
?
\"
aspect
\"
]
by
looking
at
their
second
letters.
\n
The
second
letter:
\"
arson
\"
:
\"
r
\"
(18).
\"
aspect
\"
:
\"
s
\"
(19).
We
now
have:
(18)
\"
arson
\"
<
(19)
\"
aspect
\"
.
Hence,
we
have
[
\"
arson
\"
<
\"
aspect
\"
]
<
\"
census
\"
<
\"
mugho
\"
<
\"
newt
\"
<
\"
parthia
\"
<
\"
seismography
\"
.
So
the
answer
is
arson
aspect
census
mugho
newt
parthia
seismography.
\n\n
Q:
{{input}}
\n
A:
Let's
think
step
by
step."
"
include"
:
"
_cot_fewshot_template_yaml"
"
include"
:
"
_cot_fewshot_template_yaml"
"
task"
:
"
bbh_cot_fewshot_word_sorting"
"
task"
:
"
bbh_cot_fewshot_word_sorting"
filter_list
:
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.WordSortFilter
-
function
:
"
take_first"
-
name
:
"
strict-match"
filter
:
-
function
:
"
regex"
regex_pattern
:
"
((?<=The
answer
is
)(.*)(?=.)|(?<=the
answer
is
)(.*)(?=.)|(?<=The
answer:
)(.*)(?=.)|(?<=The
final
answer:
)(.*)(?=.))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/_fewshot_template_yaml
View file @
e2909b33
...
@@ -7,16 +7,22 @@ metric_list:
...
@@ -7,16 +7,22 @@ metric_list:
- metric: exact_match
- metric: exact_match
aggregation: mean
aggregation: mean
higher_is_better: true
higher_is_better: true
#
ignore_case: true
ignore_case: true
# ignore_punctuation: true
# ignore_punctuation: true
regexes_to_ignore:
- "\\.$"
- ","
- "\\\\"
- "\n"
- '"'
generation_kwargs:
generation_kwargs:
until:
until:
- "</s>"
- "</s>"
- "Q"
- "Q
:
"
- "
\n\n
"
- "
<|im_end|>
"
do_sample: false
do_sample: false
temperature: 0.0
temperature: 0.0
num_fewshot: 0
num_fewshot: 0
metadata:
metadata:
version:
1
.0
version:
2
.0
num_fewshot: 3 # will be printed in results table
num_fewshot: 3 # will be printed in results table
lm_eval/tasks/bbh/fewshot/boolean_expressions.yaml
View file @
e2909b33
...
@@ -3,3 +3,13 @@
...
@@ -3,3 +3,13 @@
"
doc_to_text"
:
"
Q:
not
(
(
not
not
True
)
)
is
\n
A:
False
\n\n
Q:
True
and
False
and
not
True
and
True
is
\n
A:
False
\n\n
Q:
not
not
(
not
(
False
)
)
is
\n
A:
True
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
not
(
(
not
not
True
)
)
is
\n
A:
False
\n\n
Q:
True
and
False
and
not
True
and
True
is
\n
A:
False
\n\n
Q:
not
not
(
not
(
False
)
)
is
\n
A:
True
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_boolean_expressions"
"
task"
:
"
bbh_fewshot_boolean_expressions"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
"
regex"
group_select
:
0
regex_pattern
:
"
\\
b(True|False)
\\
b"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/causal_judgement.yaml
View file @
e2909b33
...
@@ -3,3 +3,13 @@
...
@@ -3,3 +3,13 @@
"
doc_to_text"
:
"
Q:
How
would
a
typical
person
answer
each
of
the
following
questions
about
causation?
\n
Frank
T.,
had
an
ongoing
dispute
with
his
neighbor
over
a
stretch
of
land
and
one
day
decided
to
shoot
his
neighbor
in
the
body.
Frank
T.
had
no
experience
with
guns,
his
hand
slipped
on
the
barrel
of
the
gun,
and
the
shot
went
wild.
Nonetheless,
the
bullet
bounced
off
a
large
boulder
several
feet
away
and
hit
the
neighbor's
body,
causing
significant
injury.
Did
Frank
T.
intentionally
shoot
his
neighbor
in
the
body?
\n
Options:
\n
-
Yes
\n
-
No
\n
A:
No
\n\n
Q:
How
would
a
typical
person
answer
each
of
the
following
questions
about
causation?
\n
Suzy
and
Billy
are
working
on
a
project
that
is
very
important
for
our
nation's
security.
The
boss
tells
them
both:
\"
Be
sure
that
you
are
here
at
exactly
9
am.
It
is
absolutely
essential
that
you
arrive
at
that
time.
\"
Both
Billy
and
Suzy
arrive
at
9
am.
As
it
happens,
there
was
a
motion
detector
installed
in
the
room
where
they
arrived.
The
motion
detector
was
set
up
to
be
triggered
if
at
least
one
person
appeared
in
the
room
at
the
same
time.
So
the
motion
detector
went
off.
Did
Billy
cause
the
motion
detector
to
go
off?
\n
Options:
\n
-
Yes
\n
-
No
\n
A:
Yes
\n\n
Q:
How
would
a
typical
person
answer
each
of
the
following
questions
about
causation?
\n
George
and
his
sister
Lena
reunite
at
their
parents'
house
for
Thanksgiving.
Whereas
George
just
got
into
medical
school,
Lena
is
unhappy
in
her
marriage
and
recently
lost
her
job.
Over
the
course
of
the
day,
George
and
Lena
get
into
a
number
of
heated
arguments.
Later
in
the
afternoon
they
play
a
game
of
darts.
They
split
the
first
two
games,
and
the
third
game
is
close
until
the
end.
Who
will
win
comes
down
to
George's
last
shot.
If
he
hits
a
high
point
region,
he
wins;
if
he
hits
a
low
point
region,
Lena
wins.
George
thinks
of
the
difficult
time
Lena
is
having,
and
he
really
wants
to
let
her
win.
He
aims
the
dart
at
the
low
point
region.
He
sets
up
his
shot
and
the
dart
lands
in
the
low
point
region.
After
his
shot,
Lena
wins
the
game
and
is
very
happy.
Did
George
hit
the
low
point
region
intentionally?
\n
Options:
\n
-
Yes
\n
-
No
\n
A:
Yes
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
How
would
a
typical
person
answer
each
of
the
following
questions
about
causation?
\n
Frank
T.,
had
an
ongoing
dispute
with
his
neighbor
over
a
stretch
of
land
and
one
day
decided
to
shoot
his
neighbor
in
the
body.
Frank
T.
had
no
experience
with
guns,
his
hand
slipped
on
the
barrel
of
the
gun,
and
the
shot
went
wild.
Nonetheless,
the
bullet
bounced
off
a
large
boulder
several
feet
away
and
hit
the
neighbor's
body,
causing
significant
injury.
Did
Frank
T.
intentionally
shoot
his
neighbor
in
the
body?
\n
Options:
\n
-
Yes
\n
-
No
\n
A:
No
\n\n
Q:
How
would
a
typical
person
answer
each
of
the
following
questions
about
causation?
\n
Suzy
and
Billy
are
working
on
a
project
that
is
very
important
for
our
nation's
security.
The
boss
tells
them
both:
\"
Be
sure
that
you
are
here
at
exactly
9
am.
It
is
absolutely
essential
that
you
arrive
at
that
time.
\"
Both
Billy
and
Suzy
arrive
at
9
am.
As
it
happens,
there
was
a
motion
detector
installed
in
the
room
where
they
arrived.
The
motion
detector
was
set
up
to
be
triggered
if
at
least
one
person
appeared
in
the
room
at
the
same
time.
So
the
motion
detector
went
off.
Did
Billy
cause
the
motion
detector
to
go
off?
\n
Options:
\n
-
Yes
\n
-
No
\n
A:
Yes
\n\n
Q:
How
would
a
typical
person
answer
each
of
the
following
questions
about
causation?
\n
George
and
his
sister
Lena
reunite
at
their
parents'
house
for
Thanksgiving.
Whereas
George
just
got
into
medical
school,
Lena
is
unhappy
in
her
marriage
and
recently
lost
her
job.
Over
the
course
of
the
day,
George
and
Lena
get
into
a
number
of
heated
arguments.
Later
in
the
afternoon
they
play
a
game
of
darts.
They
split
the
first
two
games,
and
the
third
game
is
close
until
the
end.
Who
will
win
comes
down
to
George's
last
shot.
If
he
hits
a
high
point
region,
he
wins;
if
he
hits
a
low
point
region,
Lena
wins.
George
thinks
of
the
difficult
time
Lena
is
having,
and
he
really
wants
to
let
her
win.
He
aims
the
dart
at
the
low
point
region.
He
sets
up
his
shot
and
the
dart
lands
in
the
low
point
region.
After
his
shot,
Lena
wins
the
game
and
is
very
happy.
Did
George
hit
the
low
point
region
intentionally?
\n
Options:
\n
-
Yes
\n
-
No
\n
A:
Yes
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_causal_judgement"
"
task"
:
"
bbh_fewshot_causal_judgement"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
"
regex"
group_select
:
0
regex_pattern
:
"
\\
b(Yes|No|yes|no)
\\
b"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/date_understanding.yaml
View file @
e2909b33
...
@@ -3,3 +3,15 @@
...
@@ -3,3 +3,15 @@
"
doc_to_text"
:
"
Q:
Today
is
Christmas
Eve
of
1937.
What
is
the
date
10
days
ago
in
MM/DD/YYYY?
\n
Options:
\n
(A)
12/14/2026
\n
(B)
12/14/1950
\n
(C)
12/14/2007
\n
(D)
12/14/1937
\n
(E)
07/14/1938
\n
(F)
12/14/1988
\n
A:
(D)
\n\n
Q:
Tomorrow
is
11/12/2019.
What
is
the
date
one
year
ago
from
today
in
MM/DD/YYYY?
\n
Options:
\n
(A)
09/04/2018
\n
(B)
11/11/2018
\n
(C)
08/25/2018
\n
(D)
11/02/2018
\n
(E)
11/04/2018
\n
A:
(B)
\n\n
Q:
Jane
and
John
married
on
Jan
2,
1958.
It
is
their
5-year
anniversary
today.
What
is
the
date
tomorrow
in
MM/DD/YYYY?
\n
Options:
\n
(A)
01/11/1961
\n
(B)
01/03/1963
\n
(C)
01/18/1961
\n
(D)
10/14/1960
\n
(E)
01/03/1982
\n
(F)
12/03/1960
\n
A:
(B)
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
Today
is
Christmas
Eve
of
1937.
What
is
the
date
10
days
ago
in
MM/DD/YYYY?
\n
Options:
\n
(A)
12/14/2026
\n
(B)
12/14/1950
\n
(C)
12/14/2007
\n
(D)
12/14/1937
\n
(E)
07/14/1938
\n
(F)
12/14/1988
\n
A:
(D)
\n\n
Q:
Tomorrow
is
11/12/2019.
What
is
the
date
one
year
ago
from
today
in
MM/DD/YYYY?
\n
Options:
\n
(A)
09/04/2018
\n
(B)
11/11/2018
\n
(C)
08/25/2018
\n
(D)
11/02/2018
\n
(E)
11/04/2018
\n
A:
(B)
\n\n
Q:
Jane
and
John
married
on
Jan
2,
1958.
It
is
their
5-year
anniversary
today.
What
is
the
date
tomorrow
in
MM/DD/YYYY?
\n
Options:
\n
(A)
01/11/1961
\n
(B)
01/03/1963
\n
(C)
01/18/1961
\n
(D)
10/14/1960
\n
(E)
01/03/1982
\n
(F)
12/03/1960
\n
A:
(B)
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_date_understanding"
"
task"
:
"
bbh_fewshot_date_understanding"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
0
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/disambiguation_qa.yaml
View file @
e2909b33
...
@@ -3,3 +3,15 @@
...
@@ -3,3 +3,15 @@
"
doc_to_text"
:
"
Q:
In
the
following
sentences,
explain
the
antecedent
of
the
pronoun
(which
thing
the
pronoun
refers
to),
or
state
that
it
is
ambiguous.
\n
Sentence:
The
chief
told
the
counselor
that
they
took
the
day
off.
\n
Options:
\n
(A)
The
chief
took
the
day
off
\n
(B)
The
counselor
took
the
day
off
\n
(C)
Ambiguous
\n
A:
(A)
\n\n
Q:
In
the
following
sentences,
explain
the
antecedent
of
the
pronoun
(which
thing
the
pronoun
refers
to),
or
state
that
it
is
ambiguous.
\n
Sentence:
The
manager
sent
a
message
to
the
secretary,
but
he
didn't
reply
yet.
\n
Options:
\n
(A)
The
secretary
didn't
reply
yet
\n
(B)
The
manager
didn't
reply
yet
\n
(C)
Ambiguous
\n
A:
(A)
\n\n
Q:
In
the
following
sentences,
explain
the
antecedent
of
the
pronoun
(which
thing
the
pronoun
refers
to),
or
state
that
it
is
ambiguous.
\n
Sentence:
Bailey
will
plan
to
meet
the
director
at
his
office
\n
Options:
\n
(A)
It
will
be
Bailey's
office
\n
(B)
It
will
be
the
director's
office
\n
(C)
Ambiguous
\n
A:
(C)
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
In
the
following
sentences,
explain
the
antecedent
of
the
pronoun
(which
thing
the
pronoun
refers
to),
or
state
that
it
is
ambiguous.
\n
Sentence:
The
chief
told
the
counselor
that
they
took
the
day
off.
\n
Options:
\n
(A)
The
chief
took
the
day
off
\n
(B)
The
counselor
took
the
day
off
\n
(C)
Ambiguous
\n
A:
(A)
\n\n
Q:
In
the
following
sentences,
explain
the
antecedent
of
the
pronoun
(which
thing
the
pronoun
refers
to),
or
state
that
it
is
ambiguous.
\n
Sentence:
The
manager
sent
a
message
to
the
secretary,
but
he
didn't
reply
yet.
\n
Options:
\n
(A)
The
secretary
didn't
reply
yet
\n
(B)
The
manager
didn't
reply
yet
\n
(C)
Ambiguous
\n
A:
(A)
\n\n
Q:
In
the
following
sentences,
explain
the
antecedent
of
the
pronoun
(which
thing
the
pronoun
refers
to),
or
state
that
it
is
ambiguous.
\n
Sentence:
Bailey
will
plan
to
meet
the
director
at
his
office
\n
Options:
\n
(A)
It
will
be
Bailey's
office
\n
(B)
It
will
be
the
director's
office
\n
(C)
Ambiguous
\n
A:
(C)
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_disambiguation_qa"
"
task"
:
"
bbh_fewshot_disambiguation_qa"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
0
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/dyck_languages.yaml
View file @
e2909b33
...
@@ -3,3 +3,13 @@
...
@@ -3,3 +3,13 @@
"
doc_to_text"
:
"
Q:
Complete
the
rest
of
the
sequence,
making
sure
that
the
parentheses
are
closed
properly.
Input:
[
{
[
\n
A:
]
}
]
\n\n
Q:
Complete
the
rest
of
the
sequence,
making
sure
that
the
parentheses
are
closed
properly.
Input:
<
>
(
(
[
[
(
{
}
)
[
<
>
]
]
\n
A:
]
)
)
\n\n
Q:
Complete
the
rest
of
the
sequence,
making
sure
that
the
parentheses
are
closed
properly.
Input:
<
[
<
[
{
<
[
]
<
{
}
>
>
}
]
>
{
{
(
)
}
{
<
[
<
>
]
>
}
\n
A:
}
]
>
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
Complete
the
rest
of
the
sequence,
making
sure
that
the
parentheses
are
closed
properly.
Input:
[
{
[
\n
A:
]
}
]
\n\n
Q:
Complete
the
rest
of
the
sequence,
making
sure
that
the
parentheses
are
closed
properly.
Input:
<
>
(
(
[
[
(
{
}
)
[
<
>
]
]
\n
A:
]
)
)
\n\n
Q:
Complete
the
rest
of
the
sequence,
making
sure
that
the
parentheses
are
closed
properly.
Input:
<
[
<
[
{
<
[
]
<
{
}
>
>
}
]
>
{
{
(
)
}
{
<
[
<
>
]
>
}
\n
A:
}
]
>
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_dyck_languages"
"
task"
:
"
bbh_fewshot_dyck_languages"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
"
regex"
group_select
:
0
regex_pattern
:
"
(?<=
)([
\"
\\
[
\\
(<{}>
\\
)
\\
]]+)|([
\"
\\
[
\\
(<{}>
\\
)
\\
]]+)"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/formal_fallacies.yaml
View file @
e2909b33
...
@@ -3,3 +3,13 @@
...
@@ -3,3 +3,13 @@
"
doc_to_text"
:
"
Q:
\"
It
is
not
always
easy
to
see
who
is
related
to
whom
--
and
in
which
ways.
The
following
argument
pertains
to
this
question:
To
begin
with,
Lesley
is
a
close
friend
of
Fernando.
Moreover,
being
a
close
friend
of
Fernando
or
a
schoolmate
of
Lowell
is
sufficient
for
being
a
great-grandfather
of
Leroy.
It
follows
that
Lesley
is
a
great-grandfather
of
Leroy.
\"\n
Is
the
argument,
given
the
explicitly
stated
premises,
deductively
valid
or
invalid?
\n
Options:
\n
-
valid
\n
-
invalid
\n
A:
valid
\n\n
Q:
\"
It
is
not
always
easy
to
see
who
is
related
to
whom
--
and
in
which
ways.
The
following
argument
pertains
to
this
question:
Whoever
is
not
a
great-grandfather
of
Clyde
is
a
stepbrother
of
Brian.
Being
an
ancestor
of
Dana
is
sufficient
for
not
being
a
great-grandfather
of
Clyde.
We
may
conclude:
Everyone
who
is
an
ancestor
of
Dana
is
a
stepbrother
of
Brian,
too.
\"\n
Is
the
argument,
given
the
explicitly
stated
premises,
deductively
valid
or
invalid?
\n
Options:
\n
-
valid
\n
-
invalid
\n
A:
valid
\n\n
Q:
\"
It
is
not
always
easy
to
grasp
who
is
consuming
which
products.
The
following
argument
pertains
to
this
question:
Every
infrequent
user
of
Paul
Mitchell
shampoo
is
either
a
rare
consumer
of
Nioxin
shampoo
or
a
loyal
buyer
of
Caress
soap,
or
both.
No
regular
consumer
of
Lush
soap
is
a
rare
consumer
of
Nioxin
shampoo
and,
in
the
same
time,
a
loyal
buyer
of
Caress
soap.
It
follows
that
whoever
is
an
infrequent
user
of
Paul
Mitchell
shampoo
is
not
a
regular
consumer
of
Lush
soap.
\"\n
Is
the
argument,
given
the
explicitly
stated
premises,
deductively
valid
or
invalid?
\n
Options:
\n
-
valid
\n
-
invalid
\n
A:
invalid
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
\"
It
is
not
always
easy
to
see
who
is
related
to
whom
--
and
in
which
ways.
The
following
argument
pertains
to
this
question:
To
begin
with,
Lesley
is
a
close
friend
of
Fernando.
Moreover,
being
a
close
friend
of
Fernando
or
a
schoolmate
of
Lowell
is
sufficient
for
being
a
great-grandfather
of
Leroy.
It
follows
that
Lesley
is
a
great-grandfather
of
Leroy.
\"\n
Is
the
argument,
given
the
explicitly
stated
premises,
deductively
valid
or
invalid?
\n
Options:
\n
-
valid
\n
-
invalid
\n
A:
valid
\n\n
Q:
\"
It
is
not
always
easy
to
see
who
is
related
to
whom
--
and
in
which
ways.
The
following
argument
pertains
to
this
question:
Whoever
is
not
a
great-grandfather
of
Clyde
is
a
stepbrother
of
Brian.
Being
an
ancestor
of
Dana
is
sufficient
for
not
being
a
great-grandfather
of
Clyde.
We
may
conclude:
Everyone
who
is
an
ancestor
of
Dana
is
a
stepbrother
of
Brian,
too.
\"\n
Is
the
argument,
given
the
explicitly
stated
premises,
deductively
valid
or
invalid?
\n
Options:
\n
-
valid
\n
-
invalid
\n
A:
valid
\n\n
Q:
\"
It
is
not
always
easy
to
grasp
who
is
consuming
which
products.
The
following
argument
pertains
to
this
question:
Every
infrequent
user
of
Paul
Mitchell
shampoo
is
either
a
rare
consumer
of
Nioxin
shampoo
or
a
loyal
buyer
of
Caress
soap,
or
both.
No
regular
consumer
of
Lush
soap
is
a
rare
consumer
of
Nioxin
shampoo
and,
in
the
same
time,
a
loyal
buyer
of
Caress
soap.
It
follows
that
whoever
is
an
infrequent
user
of
Paul
Mitchell
shampoo
is
not
a
regular
consumer
of
Lush
soap.
\"\n
Is
the
argument,
given
the
explicitly
stated
premises,
deductively
valid
or
invalid?
\n
Options:
\n
-
valid
\n
-
invalid
\n
A:
invalid
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_formal_fallacies"
"
task"
:
"
bbh_fewshot_formal_fallacies"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
"
regex"
group_select
:
0
regex_pattern
:
"
\\
b(valid|invalid)
\\
b"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/geometric_shapes.yaml
View file @
e2909b33
...
@@ -3,3 +3,15 @@
...
@@ -3,3 +3,15 @@
"
doc_to_text"
:
"
Q:
This
SVG
path
element
<path
d=
\"
M
31.00,73.00
L
32.00,59.00
L
44.00,50.00
L
49.00,41.00
L
64.00,37.00
L
71.00,55.00
L
64.00,76.00
L
52.00,61.00
L
31.00,73.00
\"
/>
draws
a
\n
Options:
\n
(A)
circle
\n
(B)
heptagon
\n
(C)
hexagon
\n
(D)
kite
\n
(E)
line
\n
(F)
octagon
\n
(G)
pentagon
\n
(H)
rectangle
\n
(I)
sector
\n
(J)
triangle
\n
A:
(F)
\n\n
Q:
This
SVG
path
element
<path
d=
\"
M
14.19,26.04
L
51.43,39.21
L
58.44,36.69
L
56.63,30.17
L
48.53,26.66
L
14.19,26.04
\"
/>
draws
a
\n
Options:
\n
(A)
circle
\n
(B)
heptagon
\n
(C)
hexagon
\n
(D)
kite
\n
(E)
line
\n
(F)
octagon
\n
(G)
pentagon
\n
(H)
rectangle
\n
(I)
sector
\n
(J)
triangle
\n
A:
(G)
\n\n
Q:
This
SVG
path
element
<path
d=
\"
M
41.00,43.00
L
37.00,34.00
L
41.00,33.00
L
45.00,34.00
L
41.00,43.00
\"
/>
draws
a
\n
Options:
\n
(A)
circle
\n
(B)
heptagon
\n
(C)
hexagon
\n
(D)
kite
\n
(E)
line
\n
(F)
octagon
\n
(G)
pentagon
\n
(H)
rectangle
\n
(I)
sector
\n
(J)
triangle
\n
A:
(D)
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
This
SVG
path
element
<path
d=
\"
M
31.00,73.00
L
32.00,59.00
L
44.00,50.00
L
49.00,41.00
L
64.00,37.00
L
71.00,55.00
L
64.00,76.00
L
52.00,61.00
L
31.00,73.00
\"
/>
draws
a
\n
Options:
\n
(A)
circle
\n
(B)
heptagon
\n
(C)
hexagon
\n
(D)
kite
\n
(E)
line
\n
(F)
octagon
\n
(G)
pentagon
\n
(H)
rectangle
\n
(I)
sector
\n
(J)
triangle
\n
A:
(F)
\n\n
Q:
This
SVG
path
element
<path
d=
\"
M
14.19,26.04
L
51.43,39.21
L
58.44,36.69
L
56.63,30.17
L
48.53,26.66
L
14.19,26.04
\"
/>
draws
a
\n
Options:
\n
(A)
circle
\n
(B)
heptagon
\n
(C)
hexagon
\n
(D)
kite
\n
(E)
line
\n
(F)
octagon
\n
(G)
pentagon
\n
(H)
rectangle
\n
(I)
sector
\n
(J)
triangle
\n
A:
(G)
\n\n
Q:
This
SVG
path
element
<path
d=
\"
M
41.00,43.00
L
37.00,34.00
L
41.00,33.00
L
45.00,34.00
L
41.00,43.00
\"
/>
draws
a
\n
Options:
\n
(A)
circle
\n
(B)
heptagon
\n
(C)
hexagon
\n
(D)
kite
\n
(E)
line
\n
(F)
octagon
\n
(G)
pentagon
\n
(H)
rectangle
\n
(I)
sector
\n
(J)
triangle
\n
A:
(D)
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_geometric_shapes"
"
task"
:
"
bbh_fewshot_geometric_shapes"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
0
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/hyperbaton.yaml
View file @
e2909b33
...
@@ -3,3 +3,15 @@
...
@@ -3,3 +3,15 @@
"
doc_to_text"
:
"
Q:
Which
sentence
has
the
correct
adjective
order:
\n
Options:
\n
(A)
rubber
terrible
ship
\n
(B)
terrible
rubber
ship
\n
A:
(B)
\n\n
Q:
Which
sentence
has
the
correct
adjective
order:
\n
Options:
\n
(A)
repulsive
small
Brazilian
exercise
ship
\n
(B)
Brazilian
repulsive
exercise
small
ship
\n
A:
(A)
\n\n
Q:
Which
sentence
has
the
correct
adjective
order:
\n
Options:
\n
(A)
blue
gold
wonderful
square
shoe
\n
(B)
wonderful
square
blue
gold
shoe
\n
A:
(B)
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
Which
sentence
has
the
correct
adjective
order:
\n
Options:
\n
(A)
rubber
terrible
ship
\n
(B)
terrible
rubber
ship
\n
A:
(B)
\n\n
Q:
Which
sentence
has
the
correct
adjective
order:
\n
Options:
\n
(A)
repulsive
small
Brazilian
exercise
ship
\n
(B)
Brazilian
repulsive
exercise
small
ship
\n
A:
(A)
\n\n
Q:
Which
sentence
has
the
correct
adjective
order:
\n
Options:
\n
(A)
blue
gold
wonderful
square
shoe
\n
(B)
wonderful
square
blue
gold
shoe
\n
A:
(B)
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_hyperbaton"
"
task"
:
"
bbh_fewshot_hyperbaton"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
0
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/logical_deduction_five_objects.yaml
View file @
e2909b33
...
@@ -3,3 +3,15 @@
...
@@ -3,3 +3,15 @@
"
doc_to_text"
:
"
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
In
a
golf
tournament,
there
were
three
golfers:
Amy,
Eli,
and
Eve.
Eve
finished
above
Amy.
Eli
finished
below
Amy.
\n
Options:
\n
(A)
Amy
finished
last
\n
(B)
Eli
finished
last
\n
(C)
Eve
finished
last
\n
A:
(B)
\n\n
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
On
a
shelf,
there
are
three
books:
a
white
book,
a
green
book,
and
an
orange
book.
The
green
book
is
to
the
right
of
the
white
book.
The
orange
book
is
the
rightmost.
\n
Options:
\n
(A)
The
white
book
is
the
leftmost
\n
(B)
The
green
book
is
the
leftmost
\n
(C)
The
orange
book
is
the
leftmost
\n
A:
(A)
\n\n
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
On
a
shelf,
there
are
three
books:
a
red
book,
a
gray
book,
and
a
white
book.
The
white
book
is
to
the
left
of
the
gray
book.
The
red
book
is
the
second
from
the
left.
\n
Options:
\n
(A)
The
red
book
is
the
leftmost
\n
(B)
The
gray
book
is
the
leftmost
\n
(C)
The
white
book
is
the
leftmost
\n
A:
(C)
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
In
a
golf
tournament,
there
were
three
golfers:
Amy,
Eli,
and
Eve.
Eve
finished
above
Amy.
Eli
finished
below
Amy.
\n
Options:
\n
(A)
Amy
finished
last
\n
(B)
Eli
finished
last
\n
(C)
Eve
finished
last
\n
A:
(B)
\n\n
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
On
a
shelf,
there
are
three
books:
a
white
book,
a
green
book,
and
an
orange
book.
The
green
book
is
to
the
right
of
the
white
book.
The
orange
book
is
the
rightmost.
\n
Options:
\n
(A)
The
white
book
is
the
leftmost
\n
(B)
The
green
book
is
the
leftmost
\n
(C)
The
orange
book
is
the
leftmost
\n
A:
(A)
\n\n
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
On
a
shelf,
there
are
three
books:
a
red
book,
a
gray
book,
and
a
white
book.
The
white
book
is
to
the
left
of
the
gray
book.
The
red
book
is
the
second
from
the
left.
\n
Options:
\n
(A)
The
red
book
is
the
leftmost
\n
(B)
The
gray
book
is
the
leftmost
\n
(C)
The
white
book
is
the
leftmost
\n
A:
(C)
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_logical_deduction_five_objects"
"
task"
:
"
bbh_fewshot_logical_deduction_five_objects"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
0
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
lm_eval/tasks/bbh/fewshot/logical_deduction_seven_objects.yaml
View file @
e2909b33
...
@@ -3,3 +3,15 @@
...
@@ -3,3 +3,15 @@
"
doc_to_text"
:
"
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
In
a
golf
tournament,
there
were
three
golfers:
Amy,
Eli,
and
Eve.
Eve
finished
above
Amy.
Eli
finished
below
Amy.
\n
Options:
\n
(A)
Amy
finished
last
\n
(B)
Eli
finished
last
\n
(C)
Eve
finished
last
\n
A:
(B)
\n\n
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
On
a
shelf,
there
are
three
books:
a
white
book,
a
green
book,
and
an
orange
book.
The
green
book
is
to
the
right
of
the
white
book.
The
orange
book
is
the
rightmost.
\n
Options:
\n
(A)
The
white
book
is
the
leftmost
\n
(B)
The
green
book
is
the
leftmost
\n
(C)
The
orange
book
is
the
leftmost
\n
A:
(A)
\n\n
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
On
a
shelf,
there
are
three
books:
a
red
book,
a
gray
book,
and
a
white
book.
The
white
book
is
to
the
left
of
the
gray
book.
The
red
book
is
the
second
from
the
left.
\n
Options:
\n
(A)
The
red
book
is
the
leftmost
\n
(B)
The
gray
book
is
the
leftmost
\n
(C)
The
white
book
is
the
leftmost
\n
A:
(C)
\n\n
Q:
{{input}}
\n
A:"
"
doc_to_text"
:
"
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
In
a
golf
tournament,
there
were
three
golfers:
Amy,
Eli,
and
Eve.
Eve
finished
above
Amy.
Eli
finished
below
Amy.
\n
Options:
\n
(A)
Amy
finished
last
\n
(B)
Eli
finished
last
\n
(C)
Eve
finished
last
\n
A:
(B)
\n\n
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
On
a
shelf,
there
are
three
books:
a
white
book,
a
green
book,
and
an
orange
book.
The
green
book
is
to
the
right
of
the
white
book.
The
orange
book
is
the
rightmost.
\n
Options:
\n
(A)
The
white
book
is
the
leftmost
\n
(B)
The
green
book
is
the
leftmost
\n
(C)
The
orange
book
is
the
leftmost
\n
A:
(A)
\n\n
Q:
The
following
paragraphs
each
describe
a
set
of
three
objects
arranged
in
a
fixed
order.
The
statements
are
logically
consistent
within
each
paragraph.
On
a
shelf,
there
are
three
books:
a
red
book,
a
gray
book,
and
a
white
book.
The
white
book
is
to
the
left
of
the
gray
book.
The
red
book
is
the
second
from
the
left.
\n
Options:
\n
(A)
The
red
book
is
the
leftmost
\n
(B)
The
gray
book
is
the
leftmost
\n
(C)
The
white
book
is
the
leftmost
\n
A:
(C)
\n\n
Q:
{{input}}
\n
A:"
"
include"
:
"
_fewshot_template_yaml"
"
include"
:
"
_fewshot_template_yaml"
"
task"
:
"
bbh_fewshot_logical_deduction_seven_objects"
"
task"
:
"
bbh_fewshot_logical_deduction_seven_objects"
filter_list
:
-
name
:
"
strict-match"
filter
:
-
function
:
"
take_first"
-
name
:
"
flexible-extract"
filter
:
-
function
:
!function
utils.MultiChoiceRegexFilter
group_select
:
0
ignore_case
:
true
ignore_punctuation
:
true
regex_pattern
:
"
(
\\
([A-Z]
\\
))"
-
function
:
"
take_first"
Prev
1
2
3
Next
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment