Add files using upload-large-folder tool

lm-evaluation-harness/lm_eval/tasks/aclue/README.md

@@ -0,0 +1,50 @@
+# ACLUE
+
+### Paper
+
+Can Large Language Model Comprehend Ancient Chinese? A Preliminary Test on ACLUE
+https://arxiv.org/abs/2310.09550
+
+The Ancient Chinese Language Understanding Evaluation (ACLUE) is an evaluation benchmark focused on ancient Chinese language comprehension. It aims to assess the performance of large-scale language models on understanding ancient Chinese. The benchmark comprises 15 tasks spanning various domains, including lexical, syntactic, semantic, inference, and knowledge. ACLUE's tasks are derived from a combination of manually curated questions from publicly available resources, and automatically
+generated questions from classical Chinese language corpora. The range of questions span from the Xia dynasty (2070 BCE) to the Ming dynasty (1368 CE). ACLUE adopts a multiple-choice question format for all tasks.
+
+Homepage: https://github.com/isen-zhang/ACLUE
+
+### Citation
+
+```bibtex
+@inproceedings{zhang-li-2023-large,
+    title = "Can Large Langauge Model Comprehend {A}ncient {C}hinese? A Preliminary Test on {ACLUE}",
+    author = "Zhang, Yixuan  and Li, Haonan",
+    booktitle = "Proceedings of the Ancient Language Processing Workshop",
+    month = sep,
+    year = "2023",
+    address = "Varna, Bulgaria",
+    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
+    url = "https://aclanthology.org/2023.alp-1.9",
+    pages = "80--87"
+}
+```
+
+### Groups and Tasks
+
+#### Groups
+
+- `aclue`: All 15 subjects of the ACLUE dataset, evaluated following the methodology in CMMLU's original implementation.
+
+#### Tasks
+
+The following tasks evaluate subjects in the ACLUE dataset using loglikelihood-based multiple-choice scoring:
+- `aclue_{subject_english}`
+
+### Checklist
+
+* [x] Is the task an existing benchmark in the literature?
+  * [x] Have you referenced the original paper that introduced the task?
+  * [x] If yes, does the original paper provide a reference implementation?
+    * [x] Yes, original implementation contributed by author of the benchmark
+
+If other tasks on this dataset are already supported:
+* [x] Is the "Main" variant of this task clearly denoted?
+* [x] Have you provided a short sentence in a README on what each new variant adds / evaluates?
+* [x] Have you noted which, if any, published evaluation setups are matched by this variant?

lm-evaluation-harness/lm_eval/tasks/aclue/_default_template_yaml

@@ -0,0 +1,19 @@
+group: aclue
+dataset_path: tyouisen/aclue
+test_split: test
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+output_type: multiple_choice
+doc_to_text: "{{Question.strip()}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\n答案："
+doc_to_choice: ["A", "B", "C", "D"]
+doc_to_target: "{{['A', 'B', 'C', 'D'].index(Answer)}}"
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 0.0

lm-evaluation-harness/lm_eval/tasks/aclue/_generate_configs.py

@@ -0,0 +1,81 @@
+"""
+Take in a YAML, and output all other splits with this YAML
+"""
+import argparse
+import os
+
+import yaml
+from tqdm import tqdm
+
+from lm_eval.utils import eval_logger
+
+
+SUBJECTS = {
+    "古文单字多义": "polysemy_resolution",
+    "诗词情感分类": "poetry_sentiment_analysis",
+    "古汉语命名体识别": "named_entity_recognition",
+    "古汉语知识": "basic_ancient_chinese",
+    "古诗词上下句预测": "poetry_context_prediction",
+    "古文断句": "sentence_segmentation",
+    "对联": "couplet_prediction",
+    "古诗词曲鉴赏": "poetry_appreciate",
+    "国学常识": "ancient_chinese_culture",
+    "古音学": "ancient_phonetics",
+    "通假字": "homographic_character_resolution",
+    "古代文学知识": "ancient_literature",
+    "医古文": "ancient_medical",
+    "古诗词质量评估": "poetry_quality_assessment",
+    "古文阅读理解": "reading_comprehension",
+}
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--base_yaml_path", required=True)
+    parser.add_argument("--save_prefix_path", default="aclue")
+    parser.add_argument("--cot_prompt_path", default=None)
+    parser.add_argument("--task_prefix", default="")
+    return parser.parse_args()
+
+
+if __name__ == "__main__":
+    args = parse_args()
+
+    # get filename of base_yaml so we can `"include": ` it in our other YAMLs.
+    base_yaml_name = os.path.split(args.base_yaml_path)[-1]
+    with open(args.base_yaml_path, encoding="utf-8") as f:
+        base_yaml = yaml.full_load(f)
+
+    if args.cot_prompt_path is not None:
+        import json
+
+        with open(args.cot_prompt_path, encoding="utf-8") as f:
+            cot_file = json.load(f)
+
+    for subject_zh, subject_eng in tqdm(SUBJECTS.items()):
+        if args.cot_prompt_path is not None:
+            description = cot_file[subject_eng]
+        else:
+            description = (
+                f"以下是关于{subject_zh}的单项选择题，请直接给出正确答案的选项。\n\n"
+            )
+
+        yaml_dict = {
+            "include": base_yaml_name,
+            "task": f"aclue_{args.task_prefix}_{subject_eng}"
+            if args.task_prefix != ""
+            else f"aclue_{subject_eng}",
+            "dataset_name": subject_eng,
+            "description": description,
+        }
+
+        file_save_path = args.save_prefix_path + f"_{subject_eng}.yaml"
+        eval_logger.info(f"Saving yaml for subset {subject_eng} to {file_save_path}")
+        with open(file_save_path, "w", encoding="utf-8") as yaml_file:
+            yaml.dump(
+                yaml_dict,
+                yaml_file,
+                width=float("inf"),
+                allow_unicode=True,
+                default_style='"',
+            )

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_ancient_chinese_culture.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "ancient_chinese_culture"
+"description": "以下是关于国学常识的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_ancient_chinese_culture"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_ancient_literature.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "ancient_literature"
+"description": "以下是关于古代文学知识的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_ancient_literature"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_ancient_medical.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "ancient_medical"
+"description": "以下是关于医古文的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_ancient_medical"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_ancient_phonetics.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "ancient_phonetics"
+"description": "以下是关于古音学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_ancient_phonetics"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_basic_ancient_chinese.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "basic_ancient_chinese"
+"description": "以下是关于古汉语知识的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_basic_ancient_chinese"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_couplet_prediction.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "couplet_prediction"
+"description": "以下是关于对联的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_couplet_prediction"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_homographic_character_resolution.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "homographic_character_resolution"
+"description": "以下是关于通假字的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_homographic_character_resolution"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_named_entity_recognition.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "named_entity_recognition"
+"description": "以下是关于古汉语命名体识别的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_named_entity_recognition"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_poetry_appreciate.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "poetry_appreciate"
+"description": "以下是关于古诗词曲鉴赏的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_poetry_appreciate"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_poetry_context_prediction.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "poetry_context_prediction"
+"description": "以下是关于古诗词上下句预测的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_poetry_context_prediction"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_poetry_quality_assessment.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "poetry_quality_assessment"
+"description": "以下是关于古诗词质量评估的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_poetry_quality_assessment"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_poetry_sentiment_analysis.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "poetry_sentiment_analysis"
+"description": "以下是关于诗词情感分类的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_poetry_sentiment_analysis"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_polysemy_resolution.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "polysemy_resolution"
+"description": "以下是关于古文单字多义的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_polysemy_resolution"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_reading_comprehension.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "reading_comprehension"
+"description": "以下是关于古文阅读理解的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_reading_comprehension"

lm-evaluation-harness/lm_eval/tasks/aclue/aclue_sentence_segmentation.yaml

@@ -0,0 +1,4 @@
+"dataset_name": "sentence_segmentation"
+"description": "以下是关于古文断句的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "aclue_sentence_segmentation"

lm-evaluation-harness/lm_eval/tasks/bbh/fewshot/date_understanding.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "date_understanding"
+"description": "Infer the date from context.\n\n"
+"doc_to_text": "Q: Today is Christmas Eve of 1937. What is the date 10 days ago in MM/DD/YYYY?\nOptions:\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\nA: (D)\n\nQ: Tomorrow is 11/12/2019. What is the date one year ago from today in MM/DD/YYYY?\nOptions:\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\nA: (B)\n\nQ: Jane and John married on Jan 2, 1958. It is their 5-year anniversary today. What is the date tomorrow in MM/DD/YYYY?\nOptions:\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\nA: (B)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_date_understanding"

lm-evaluation-harness/lm_eval/tasks/bbh/fewshot/geometric_shapes.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "geometric_shapes"
+"description": "Name geometric shapes from their SVG paths.\n\n"
+"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\nOptions:\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\nA: (F)\n\nQ: 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\nOptions:\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\nA: (G)\n\nQ: 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\nOptions:\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\nA: (D)\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_geometric_shapes"

lm-evaluation-harness/lm_eval/tasks/bbh/fewshot/movie_recommendation.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "movie_recommendation"
+"description": "Recommend movies similar to the given list of movies.\n\n"
+"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"

lm-evaluation-harness/lm_eval/tasks/bbh/fewshot/salient_translation_error_detection.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "salient_translation_error_detection"
+"description": "Detect the type of error in an English translation of a German source sentence.\n\n"
+"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"

lm-evaluation-harness/lm_eval/tasks/bbh/fewshot/snarks.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "snarks"
+"description": "Determine which of two sentences is sarcastic.\n\nAccording 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?\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"

lm-evaluation-harness/lm_eval/tasks/bbh/fewshot/temporal_sequences.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "temporal_sequences"
+"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?\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"

lm-evaluation-harness/lm_eval/tasks/bbh/fewshot/tracking_shuffled_objects_five_objects.yaml

@@ -0,0 +1,5 @@
+"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"
+"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"

lm-evaluation-harness/lm_eval/tasks/bbh/fewshot/tracking_shuffled_objects_three_objects.yaml

@@ -0,0 +1,5 @@
+"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"
+"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"

lm-evaluation-harness/lm_eval/tasks/bbh/fewshot/word_sorting.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "word_sorting"
+"description": "Sort a list of words.\n\n"
+"doc_to_text": "Q: Sort the following words alphabetically: List: oven costume counterpart\nA: costume counterpart oven\n\nQ: Sort the following words alphabetically: List: hypochlorite ponderosa phone credulity\nA: credulity hypochlorite phone ponderosa\n\nQ: Sort the following words alphabetically: List: newt arson parthia seismography mugho aspect census\nA: arson aspect census mugho newt parthia seismography\n\nQ: {{input}}\nA:"
+"include": "_fewshot_template_yaml"
+"task": "bbh_fewshot_word_sorting"

lm-evaluation-harness/lm_eval/tasks/bbh/zeroshot/_zeroshot_template_yaml

@@ -0,0 +1,27 @@
+group: bbh_zeroshot
+dataset_path: lukaemon/bbh
+output_type: generate_until
+test_split: test
+doc_to_target: "{{target}}"
+metric_list:
+  - metric: exact_match
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    # ignore_punctuation: true
+    regexes_to_ignore:
+      - "\\.$"
+      - ","
+      - "\n"
+      - "\\\\"
+      - '"'
+generation_kwargs:
+  until:
+    - "</s>"
+    - "Q:"
+    - "<|im_end|>"
+  do_sample: false
+  temperature: 0.0
+num_fewshot: 0
+metadata:
+  version: 2.0

lm-evaluation-harness/lm_eval/tasks/bbh/zeroshot/boolean_expressions.yaml

@@ -0,0 +1,16 @@
+"dataset_name": "boolean_expressions"
+"description": "Evaluate the result of a random Boolean expression.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/causal_judgement.yaml

@@ -0,0 +1,16 @@
+"dataset_name": "causal_judgement"
+"description": "Answer questions about causal attribution.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/date_understanding.yaml

@@ -0,0 +1,18 @@
+"dataset_name": "date_understanding"
+"description": "Infer the date from context.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/disambiguation_qa.yaml

@@ -0,0 +1,18 @@
+"dataset_name": "disambiguation_qa"
+"description": "Clarify the meaning of sentences with ambiguous pronouns.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/dyck_languages.yaml

@@ -0,0 +1,15 @@
+"dataset_name": "dyck_languages"
+"description": "Correctly close a Dyck-n word.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/formal_fallacies.yaml

@@ -0,0 +1,16 @@
+"dataset_name": "formal_fallacies"
+"description": "Distinguish deductively valid arguments from formal fallacies.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/geometric_shapes.yaml

@@ -0,0 +1,18 @@
+"dataset_name": "geometric_shapes"
+"description": "Name geometric shapes from their SVG paths.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/hyperbaton.yaml

@@ -0,0 +1,18 @@
+"dataset_name": "hyperbaton"
+"description": "Order adjectives correctly in English sentences.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/logical_deduction_five_objects.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "logical_deduction_five_objects"
+"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/logical_deduction_seven_objects.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "logical_deduction_seven_objects"
+"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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"

lm-evaluation-harness/lm_eval/tasks/bbh/zeroshot/logical_deduction_three_objects.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "logical_deduction_three_objects"
+"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/movie_recommendation.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "movie_recommendation"
+"description": "Recommend movies similar to the given list of movies.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/multistep_arithmetic_two.yaml

@@ -0,0 +1,16 @@
+"dataset_name": "multistep_arithmetic_two"
+"description": "Solve multi-step arithmetic problems.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/navigate.yaml

@@ -0,0 +1,15 @@
+"dataset_name": "navigate"
+"description": "Given a series of navigation instructions, determine whether one would end up back at the starting point.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/object_counting.yaml

@@ -0,0 +1,15 @@
+"dataset_name": "object_counting"
+"description": "Questions that involve enumerating objects and asking the model to count them.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/penguins_in_a_table.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "penguins_in_a_table"
+"description": "Answer questions about a table of penguins and their attributes.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/reasoning_about_colored_objects.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "reasoning_about_colored_objects"
+"description": "Answer extremely simple questions about the colors of objects on a surface.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/ruin_names.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "ruin_names"
+"description": "Select the humorous edit that 'ruins' the input movie or musical artist name.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/salient_translation_error_detection.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "salient_translation_error_detection"
+"description": "Detect the type of error in an English translation of a German source sentence.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/snarks.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "snarks"
+"description": "Determine which of two sentences is sarcastic.\n\nAccording 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: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/sports_understanding.yaml

@@ -0,0 +1,19 @@
+"dataset_name": "sports_understanding"
+"description": "Determine whether an artificially constructed sentence relating to sports is plausible or not.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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-evaluation-harness/lm_eval/tasks/bbh/zeroshot/temporal_sequences.yaml

@@ -0,0 +1,17 @@
+"dataset_name": "temporal_sequences"
+"description": "Task description: Answer questions about which times certain events could have occurred.\n\n"
+"doc_to_text": "Q: {{input}}\nA:"
+"include": "_zeroshot_template_yaml"
+"task": "bbh_zeroshot_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"