transfer zeroshot improvements on bbh to fewshot

lm_eval/tasks/bbh/fewshot/logical_deduction_three_objects.yaml

@@ -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.\nOptions:\n(A) Amy finished last\n(B) Eli finished last\n(C) Eve finished last\nA: (B)\n\nQ: 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.\nOptions:\n(A) The white book is the leftmost\n(B) The green book is the leftmost\n(C) The orange book is the leftmost\nA: (A)\n\nQ: 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.\nOptions:\n(A) The red book is the leftmost\n(B) The gray book is the leftmost\n(C) The white book is the leftmost\nA: (C)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_logical_deduction_three_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/movie_recommendation.yaml

@@ -3,3 +3,15 @@
 "doc_to_text": "Q: Find a movie similar to Star Wars Episode IV - A New Hope, Indiana Jones and the Last Crusade, Star Wars Episode V - The Empire Strikes Back, The Big Lebowski:\nOptions:\n(A) Tetsuo\n(B) the Ironman\n(C) The Princess Bride\n(D) The Barkley Marathons The Race That Eats Its Young\n(E) Bug\nA: (C)\n\nQ: Find a movie similar to Twister, The Silence of the Lambs, Independence Day, Braveheart:\nOptions:\n(A) They Shoot Horses\n(B) Don't They\n(C) Forrest Gump\n(D) The Salton Sea\n(E) Extreme Days\nA: (C)\n\nQ: Find a movie similar to Minority Report, Total Recall, Inside Out, Forrest Gump:\nOptions:\n(A) Phenomena\n(B) Lilting\n(C) Catwoman\n(D) Edge of Tomorrow\nA: (D)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_movie_recommendation"
+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/multistep_arithmetic_two.yaml

@@ -3,3 +3,13 @@
 "doc_to_text": "Q: ((-5 + 9 * -4 - 0) * (4 + -7 + 0 * -5)) =\nA: 123\n\nQ: ((-9 * 7 * 7 * -9) + (4 * -9 - 8 - -4)) =\nA: 3929\n\nQ: ((-3 + 5 * 8 * -4) - (9 - 8 * -7 + -9)) =\nA: -219\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_multistep_arithmetic_two"
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.NumberParseRegexFilter
+        group_select: 0
+        regex_pattern: "([-0-9]+)"
+      - function: "take_first"

lm_eval/tasks/bbh/fewshot/navigate.yaml

@@ -3,3 +3,13 @@
 "doc_to_text": "Q: If you follow these instructions, do you return to the starting point? Turn left. Turn around. Turn left. Take 7 steps. Take 2 steps. Take 4 steps. Take 8 steps.\nOptions:\n- Yes\n- No\nA: No\n\nQ: If you follow these instructions, do you return to the starting point? Turn around. Take 1 step. Take 6 steps. Turn around. Take 6 steps. Take 9 steps. Take 1 step.\nOptions:\n- Yes\n- No\nA: No\n\nQ: If you follow these instructions, do you return to the starting point? Always face forward. Take 2 steps right. Take 9 steps left. Take 7 steps right.\nOptions:\n- Yes\n- No\nA: Yes\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_navigate"
+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/object_counting.yaml

@@ -3,3 +3,13 @@
 "doc_to_text": "Q: I have a blackberry, a clarinet, a nectarine, a plum, a strawberry, a banana, a flute, an orange, and a violin. How many fruits do I have?\nA: 6\n\nQ: I have an orange, a raspberry, two peaches, a blackberry, an apple, a grape, a nectarine, and three plums. How many fruits do I have?\nA: 11\n\nQ: I have a lettuce head, a head of broccoli, an onion, a stalk of celery, two carrots, a garlic, and a yam. How many vegetables do I have?\nA: 8\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_object_counting"
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.NumberParseRegexFilter
+        group_select: 0
+        regex_pattern: "([-0-9]+)"
+      - function: "take_first"

lm_eval/tasks/bbh/fewshot/penguins_in_a_table.yaml

@@ -3,3 +3,15 @@
 "doc_to_text": "Q: Here is a table where the first line is a header and each subsequent line is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  We now add a penguin to the table:\nJames, 12, 90, 12\nHow many penguins are less than 8 years old?\nOptions:\n(A) 1\n(B) 2\n(C) 3\n(D) 4\n(E) 5\nA: (B)\n\nQ: Here is a table where the first line is a header and each subsequent line is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  Which is the youngest penguin?\nOptions:\n(A) Louis\n(B) Bernard\n(C) Vincent\n(D) Gwen\n(E) James\nA: (B)\n\nQ: Here is a table where the first line is a header and each subsequent line is a penguin:  name, age, height (cm), weight (kg) Louis, 7, 50, 11 Bernard, 5, 80, 13 Vincent, 9, 60, 11 Gwen, 8, 70, 15  For example: the age of Louis is 7, the weight of Gwen is 15 kg, the height of Bernard is 80 cm.  What is the name of the second penguin sorted by alphabetic order?\nOptions:\n(A) Louis\n(B) Bernard\n(C) Vincent\n(D) Gwen\n(E) James\nA: (D)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_penguins_in_a_table"
+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/reasoning_about_colored_objects.yaml

@@ -3,3 +3,15 @@
 "doc_to_text": "Q: On the nightstand, there is a red pencil, a purple mug, a burgundy keychain, a fuchsia teddy bear, a black plate, and a blue stress ball. What color is the stress ball?\nOptions:\n(A) red\n(B) orange\n(C) yellow\n(D) green\n(E) blue\n(F) brown\n(G) magenta\n(H) fuchsia\n(I) mauve\n(J) teal\n(K) turquoise\n(L) burgundy\n(M) silver\n(N) gold\n(O) black\n(P) grey\n(Q) purple\n(R) pink\nA: (E)\n\nQ: On the table, you see a bunch of objects arranged in a row: a purple paperclip, a pink stress ball, a brown keychain, a green scrunchiephone charger, a mauve fidget spinner, and a burgundy pen. What is the color of the object directly to the right of the stress ball?\nOptions:\n(A) red\n(B) orange\n(C) yellow\n(D) green\n(E) blue\n(F) brown\n(G) magenta\n(H) fuchsia\n(I) mauve\n(J) teal\n(K) turquoise\n(L) burgundy\n(M) silver\n(N) gold\n(O) black\n(P) grey\n(Q) purple\n(R) pink\nA: (F)\n\nQ: On the nightstand, you see the following items arranged in a row: a teal plate, a burgundy keychain, a yellow scrunchiephone charger, an orange mug, a pink notebook, and a grey cup. How many non-orange items do you see to the left of the teal item?\nOptions:\n(A) zero\n(B) one\n(C) two\n(D) three\n(E) four\n(F) five\n(G) six\nA: (A)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_reasoning_about_colored_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/ruin_names.yaml

@@ -3,3 +3,15 @@
 "doc_to_text": "Q: Which of the following is a humorous edit of this artist or movie name: 'whitesnake'?\nOptions:\n(A) whitesnape\n(B) whitesnapke\n(C) whitesnuake\n(D) mwhitesnake\nA: (A)\n\nQ: Which of the following is a humorous edit of this artist or movie name: 'one of our dinosaurs is missing'?\nOptions:\n(A) ofne of our dinosaurs is missing\n(B) one af our dinosaurs is missing\n(C) one of our dinosaurs is pissing\n(D) one of our dinosaur is missing\nA: (C)\n\nQ: Which of the following is a humorous edit of this artist or movie name: 'counting crows'?\nOptions:\n(A) countingy crows\n(B) counting cows\n(C) courting crows\n(D) coutnting crows\nA: (B)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_ruin_names"
+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/salient_translation_error_detection.yaml

@@ -3,3 +3,15 @@
 "doc_to_text": "Q: The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error.  Source: In der Liste der Baudenkmale in Lenzen (Elbe) sind alle Baudenkmale der brandenburgischen Stadt Lenzen (Elbe) und ihrer Ortsteile aufgelistet.\nTranslation: In the list of architectural monuments in Lenzen all architectural monuments of the Brandenburg city of Lenzen and its districts are listed.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts\nA: (D)\n\nQ: The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error.  Source: Auf dieser Seite sind die Baudenkmäler der oberbayerischen Großen Kreisstadt Landsberg am Lech zusammengestellt.\nTranslation: On this page are compiled the architectural monuments of the town of Landsberg am Lech.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts\nA: (E)\n\nQ: The following translations from German to English contain a particular error. That error will be one of the following types: Named Entities: An entity (names, places, locations, etc.) is changed to a different entity. Numerical Values: Numerical values (ordinals or cardinals), dates, and/or units are changed. Modifiers or Adjectives: The modifiers and adjectives pertaining to a noun are changed. Negation or Antonyms: Introduce or remove a negation or change comparatives to their antonyms. Facts: Trivial factual errors not pertaining to the above classes are introduced in the translations. Dropped Content: A significant clause in the translation is removed. Please identify that error.  Source: Łeba ist eine Kleinstadt und ein Badeort im Powiat Lęborski der polnischen Woiwodschaft Pommern.\nTranslation: Eba is not a small town and seaside resort in the Powiat Léborski county of the Pomeranian Voivodeship of Poland.\nThe translation contains an error pertaining to\nOptions:\n(A) Modifiers or Adjectives\n(B) Numerical Values\n(C) Negation or Antonyms\n(D) Named Entities\n(E) Dropped Content\n(F) Facts\nA: (C)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_salient_translation_error_detection"
+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/snarks.yaml

@@ -3,3 +3,15 @@
 "doc_to_text": "Q: Which statement is sarcastic?\nOptions:\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\nA: (A)\n\nQ: Which statement is sarcastic?\nOptions:\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\nA: (B)\n\nQ: Which statement is sarcastic?\nOptions:\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?\nA: (A)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_snarks"
+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/sports_understanding.yaml

@@ -3,3 +3,16 @@
 "doc_to_text": "Q: Is the following sentence plausible? \"Bam Adebayo scored a reverse layup in the Western Conference Finals.\"\nA: yes\n\nQ: Is the following sentence plausible? \"Santi Cazorla scored a touchdown.\"\nA: no\n\nQ: Is the following sentence plausible? \"DeMar DeRozan was called for the goal tend.\"\nA: yes\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_sports_understanding"
+filter_list:
+  - name: "strict-match"
+    filter:
+      - function: "take_first"
+  - name: "flexible-extract"
+    filter:
+      - function: !function utils.MapRegexFilter
+        group_select: 0
+        ignore_case: true
+        regex_pattern_to_value:
+          \b(no|not plausible)\b: "no"
+          \b(yes|plausible)\b: "yes"
+      - function: "take_first"

lm_eval/tasks/bbh/fewshot/temporal_sequences.yaml

@@ -3,3 +3,15 @@
 "doc_to_text": "Q: Today, Emily went to the museum. Between what times could they have gone?\nWe know that:\nEmily woke up at 1pm.\nElizabeth saw Emily reading at the library from 2pm to 4pm.\nJessica saw Emily watching a movie at the theater from 4pm to 5pm.\nLeslie saw Emily waiting at the airport from 5pm to 6pm.\nWilliam saw Emily buying clothes at the mall from 6pm to 7pm.\nThe museum was closed after 7pm.\nBetween what times could Emily have gone to the museum?\nOptions:\n(A) 1pm to 2pm\n(B) 6pm to 7pm\n(C) 5pm to 6pm\n(D) 2pm to 4pm\nA: (A)\n\nQ: Today, Elizabeth went to the amusement park. Between what times could they have gone?\nWe know that:\nElizabeth woke up at 7am.\nDavid saw Elizabeth fixing their computer at the electronic store from 1pm to 2pm.\nSarah saw Elizabeth playing tennis at the tennis court from 2pm to 3pm.\nSusan saw Elizabeth walking towards the Statue of Liberty from 3pm to 6pm.\nAndrew saw Elizabeth taking photos near the Eiffel Tower from 6pm to 9pm.\nEmily saw Elizabeth getting a coffee at the cafe from 9pm to 10pm.\nThe amusement park was closed after 10pm.\nBetween what times could Elizabeth have gone to the amusement park?\nOptions:\n(A) 7am to 1pm\n(B) 9pm to 10pm\n(C) 1pm to 2pm\n(D) 3pm to 6pm\nA: (A)\n\nQ: Today, Tiffany went to the beach. Between what times could they have gone?\nWe know that:\nTiffany woke up at 5am.\nBetty saw Tiffany getting a coffee at the cafe from 5am to 6am.\nJessica saw Tiffany working at the office from 6am to 9am.\nJohn saw Tiffany stretching at a yoga studio from 9am to 12pm.\nSean saw Tiffany sitting on a rooftop from 12pm to 2pm.\nSarah saw Tiffany playing tennis at the tennis court from 2pm to 3pm.\nThe beach was closed after 4pm.\nBetween what times could Tiffany have gone to the beach?\nOptions:\n(A) 9am to 12pm\n(B) 12pm to 2pm\n(C) 5am to 6am\n(D) 3pm to 4pm\nA: (D)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_temporal_sequences"
+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/tracking_shuffled_objects_five_objects.yaml

@@ -3,3 +3,15 @@
 "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.\nAs 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\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: 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.\nAs 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\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: 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.\nThroughout 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\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_tracking_shuffled_objects_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/tracking_shuffled_objects_seven_objects.yaml

@@ -3,3 +3,15 @@
 "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.\nAs 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\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: 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.\nAs 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\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: 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.\nThroughout 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\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_tracking_shuffled_objects_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"

lm_eval/tasks/bbh/fewshot/tracking_shuffled_objects_three_objects.yaml

@@ -3,3 +3,15 @@
 "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.\nAs 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\nOptions:\n(A) yellow ball\n(B) blue ball\n(C) pink ball\nA: (A)\n\nQ: 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.\nAs 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\nOptions:\n(A) white ball\n(B) purple ball\n(C) pink ball\nA: (C)\n\nQ: 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.\nThroughout 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\nOptions:\n(A) Lola\n(B) Rodrigo\n(C) Patrick\nA: (C)\n\nQ: {{input}}\nA:"
 "include": "_fewshot_template_yaml"
 "task": "bbh_fewshot_tracking_shuffled_objects_three_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/utils.py

+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