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
0d5748b7
Commit
0d5748b7
authored
Dec 13, 2023
by
lintangsutawika
Browse files
added mmlu alt world prompts
parent
b9e55312
Changes
891
Hide whitespace changes
Inline
Side-by-side
Showing
20 changed files
with
127 additions
and
0 deletions
+127
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_moral_scenarios.yaml
...lds/output_variation/style_04/c/mmlu_moral_scenarios.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_nutrition.yaml
...ve_worlds/output_variation/style_04/c/mmlu_nutrition.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_philosophy.yaml
...e_worlds/output_variation/style_04/c/mmlu_philosophy.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_prehistory.yaml
...e_worlds/output_variation/style_04/c/mmlu_prehistory.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_professional_accounting.yaml
...ut_variation/style_04/c/mmlu_professional_accounting.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_professional_law.yaml
...ds/output_variation/style_04/c/mmlu_professional_law.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_professional_medicine.yaml
...tput_variation/style_04/c/mmlu_professional_medicine.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_professional_psychology.yaml
...ut_variation/style_04/c/mmlu_professional_psychology.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_public_relations.yaml
...ds/output_variation/style_04/c/mmlu_public_relations.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_security_studies.yaml
...ds/output_variation/style_04/c/mmlu_security_studies.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_sociology.yaml
...ve_worlds/output_variation/style_04/c/mmlu_sociology.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_us_foreign_policy.yaml
...s/output_variation/style_04/c/mmlu_us_foreign_policy.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_virology.yaml
...ive_worlds/output_variation/style_04/c/mmlu_virology.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_world_religions.yaml
...lds/output_variation/style_04/c/mmlu_world_religions.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/_default_template_yaml
...e_worlds/prompt_variation/style_01/_default_template_yaml
+13
-0
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/_mmlu.yaml
...u/alternative_worlds/prompt_variation/style_01/_mmlu.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/mmlu_abstract_algebra.yaml
...rlds/prompt_variation/style_01/mmlu_abstract_algebra.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/mmlu_anatomy.yaml
...native_worlds/prompt_variation/style_01/mmlu_anatomy.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/mmlu_astronomy.yaml
...tive_worlds/prompt_variation/style_01/mmlu_astronomy.yaml
+6
-0
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/mmlu_business_ethics.yaml
...orlds/prompt_variation/style_01/mmlu_business_ethics.yaml
+6
-0
No files found.
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_moral_scenarios.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
moral_scenarios"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
moral
\
\
scenarios.
\n\n
"
"
group"
:
"
mmlu_alt_ov_04c_humanities"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_moral_scenarios"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_nutrition.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
nutrition"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
nutrition.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_04c_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_nutrition"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_philosophy.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
philosophy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
philosophy.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_04c_humanities"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_philosophy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_prehistory.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
prehistory"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
prehistory.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_04c_humanities"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_prehistory"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_professional_accounting.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
professional_accounting"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
accounting.
\n\n
"
"
group"
:
"
mmlu_alt_ov_04c_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_professional_accounting"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_professional_law.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
professional_law"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
law.
\n\n
"
"
group"
:
"
mmlu_alt_ov_04c_humanities"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_professional_law"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_professional_medicine.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
professional_medicine"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
medicine.
\n\n
"
"
group"
:
"
mmlu_alt_ov_04c_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_professional_medicine"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_professional_psychology.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
professional_psychology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
professional
\
\
psychology.
\n\n
"
"
group"
:
"
mmlu_alt_ov_04c_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_professional_psychology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_public_relations.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
public_relations"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
public
\
\
relations.
\n\n
"
"
group"
:
"
mmlu_alt_ov_04c_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_public_relations"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_security_studies.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
security_studies"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
security
\
\
studies.
\n\n
"
"
group"
:
"
mmlu_alt_ov_04c_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_security_studies"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_sociology.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
sociology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
sociology.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_04c_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_sociology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_us_foreign_policy.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
us_foreign_policy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
us
\
\
foreign
policy.
\n\n
"
"
group"
:
"
mmlu_alt_ov_04c_social_sciences"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_us_foreign_policy"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_virology.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
virology"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
virology.
\n\
\n
"
"
group"
:
"
mmlu_alt_ov_04c_other"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_virology"
lm_eval/tasks/mmlu/alternative_worlds/output_variation/style_04/c/mmlu_world_religions.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
world_religions"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
world
\
\
religions.
\n\n
"
"
group"
:
"
mmlu_alt_ov_04c_humanities"
"
include"
:
"
_template_yaml"
"
task"
:
"
mmlu_alt_ov_04c_world_religions"
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/_default_template_yaml
0 → 100644
View file @
0d5748b7
dataset_path: hails/mmlu_no_train # a copy of `cais/mmlu` with no auxiliary_train split
test_split: test
fewshot_split: dev
fewshot_config:
sampler: first_n
output_type: multiple_choice
doc_to_text: "{{question.strip()}}"
doc_to_choice: choices
doc_to_target: answer
metric_list:
- metric: acc
- metric: acc_norm
- metric: brier_score
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/_mmlu.yaml
0 → 100644
View file @
0d5748b7
group
:
mmlu_alt_pv_01
task
:
-
mmlu_alt_pv_01_stem
-
mmlu_alt_pv_01_other
-
mmlu_alt_pv_01_social_sciences
-
mmlu_alt_pv_01_humanities
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/mmlu_abstract_algebra.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
abstract_algebra"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
abstract
\
\
algebra.
\n\n
"
"
group"
:
"
mmlu_alt_pv_01_stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_alt_pv_01_abstract_algebra"
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/mmlu_anatomy.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
anatomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
anatomy.
\n\
\n
"
"
group"
:
"
mmlu_alt_pv_01_stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_alt_pv_01_anatomy"
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/mmlu_astronomy.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
astronomy"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
astronomy.
\n\
\n
"
"
group"
:
"
mmlu_alt_pv_01_stem"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_alt_pv_01_astronomy"
lm_eval/tasks/mmlu/alternative_worlds/prompt_variation/style_01/mmlu_business_ethics.yaml
0 → 100644
View file @
0d5748b7
"
dataset_name"
:
"
business_ethics"
"
description"
:
"
The
following
are
multiple
choice
questions
(with
answers)
about
business
\
\
ethics.
\n\n
"
"
group"
:
"
mmlu_alt_pv_01_other"
"
include"
:
"
_default_template_yaml"
"
task"
:
"
mmlu_alt_pv_01_business_ethics"
Prev
1
…
32
33
34
35
36
37
38
39
40
…
45
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