Merge branch 'upstream' into 'mmlu-pro'

add tokenizer logs info (#1731)

See merge request shijie.yu/lm-evaluation-harness!4

lm_eval/tasks/kormedmcqa/_kormedmcqa.yaml

+group: kormedmcqa
+task:
+  - kormedmcqa_doctor
+  - kormedmcqa_nurse
+  - kormedmcqa_pharm
+aggregate_metric_list:
+  - metric: exact_match
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 0.0

lm_eval/tasks/kormedmcqa/kormedmcqa_doctor.yaml

-group: kormedmcqa
 task : kormedmcqa_doctor
 dataset_path : sean0042/KorMedMCQA
 dataset_name : doctor

lm_eval/tasks/kormedmcqa/kormedmcqa_nurse.yaml

-group: kormedmcqa
 task : kormedmcqa_nurse
 dataset_path : sean0042/KorMedMCQA
 dataset_name : nurse

lm_eval/tasks/kormedmcqa/kormedmcqa_pharm.yaml

-group: kormedmcqa
 task : kormedmcqa_pharm
 dataset_path : sean0042/KorMedMCQA
 dataset_name : pharm

lm_eval/tasks/lambada/lambada_openai.yaml

-group:
+tag:
   - lambada
 task: lambada_openai
 dataset_path: EleutherAI/lambada_openai

lm_eval/tasks/lambada/lambada_standard.yaml

-group:
+tag:
   - lambada
 task: lambada_standard
 dataset_path: lambada

lm_eval/tasks/lambada_cloze/lambada_openai_cloze.yaml

-group:
+tag:
   - lambada_cloze
 task: lambada_openai_cloze_yaml
 dataset_path: EleutherAI/lambada_openai

lm_eval/tasks/lambada_cloze/lambada_standard_cloze.yaml

-group:
+tag:
   - lambada_cloze
 task: lambada_standard_cloze_yaml
 dataset_path: lambada

lm_eval/tasks/lambada_multilingual/lambada_mt_en.yaml

-group:
+tag:
   - lambada_multilingual
 task: lambada_openai_mt_en
 dataset_path: EleutherAI/lambada_openai

lm_eval/tasks/leaderboard/README.md

+# Leaderboard evaluations
+Our goal with this group is to create an unchanging through time version of
+evaluations that will power the Open LLM Leaderboard on HuggingFace.
+
+As we want to evaluate models across capabilities, the list currently contains:
+- BBH (3-shots, multichoice)
+- GPQA (0-shot, multichoice)
+- mmlu-pro (5-shots, multichoice)
+- Musr (0-shot, multichoice)
+- ifeval (0-shot, generative)
+- Math-lvl-5 (4-shots, generative, minerva version)
+
+
+Details on the choice of those evals can be found [here](https://huggingface.co/spaces/open-llm-leaderboard/blog) !
+
+## BigBenchHard (BBH)
+
+A suite of 23 challenging BIG-Bench tasks which we call BIG-Bench Hard (BBH).
+These are the task for which prior language model evaluations did not
+outperform the average human-rater.
+
+### Paper
+
+Title: Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
+
+BIG-Bench (Srivastava et al., 2022) is a diverse evaluation suite that focuses on tasks believed to be beyond the capabilities of current language models. Language models have already made good progress on this benchmark, with the best model in the BIG-Bench paper outperforming average reported human-rater results on 65% of the BIG-Bench tasks via few-shot prompting. But on what tasks do language models fall short of average human-rater performance, and are those tasks actually unsolvable by current language models?
+In this work, we focus on a suite of 23 challenging BIG-Bench tasks which we call BIG-Bench Hard (BBH). These are the task for which prior language model evaluations did not outperform the average human-rater. We find that applying chain-of-thought (CoT) prompting to BBH tasks enables PaLM to surpass the average human-rater performance on 10 of the 23 tasks, and Codex (code-davinci-002) to surpass the average human-rater performance on 17 of the 23 tasks. Since many tasks in BBH require multi-step reasoning, few-shot prompting without CoT, as done in the BIG-Bench evaluations (Srivastava et al., 2022), substantially underestimates the best performance and capabilities of language models, which is better captured via CoT prompting. As further analysis, we explore the interaction between CoT and model scale on BBH, finding that CoT enables emergent task performance on several BBH tasks with otherwise flat scaling curves.
+
+
+- paper: https://huggingface.co/papers/2210.09261
+- Homepage: https://github.com/suzgunmirac/BIG-Bench-Hard
+
+### Citation
+
+```
+@article{suzgun2022challenging,
+  title={Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them},
+  author={Suzgun, Mirac and Scales, Nathan and Sch{\"a}rli, Nathanael and Gehrmann, Sebastian and Tay, Yi and Chung, Hyung Won and Chowdhery, Aakanksha and Le, Quoc V and Chi, Ed H and Zhou, Denny and and Wei, Jason},
+  journal={arXiv preprint arXiv:2210.09261},
+  year={2022}
+}
+```
+
+### Groups
+
+- `leaderboard_bbh`
+
+### Tasks
+
+- `leaderboard_bbh_boolean_expressions`
+- `leaderboard_bbh_causal_judgement`
+- `leaderboard_bbh_date_understanding`
+- `leaderboard_bbh_disambiguation_qa`
+- `leaderboard_bbh_dyck_languages`
+- `leaderboard_bbh_formal_fallacies`
+- `leaderboard_bbh_geometric_shapes`
+- `leaderboard_bbh_hyperbaton`
+- `leaderboard_bbh_logical_deduction_five_objects`
+- `leaderboard_bbh_logical_deduction_seven_objects`
+- `leaderboard_bbh_logical_deduction_three_objects`
+- `leaderboard_bbh_movie_recommendation`
+- `leaderboard_bbh_multistep_arithmetic_two`
+- `leaderboard_bbh_navigate`
+- `leaderboard_bbh_object_counting`
+- `leaderboard_bbh_penguins_in_a_table`
+- `leaderboard_bbh_reasoning_about_colored_objects`
+- `leaderboard_bbh_ruin_names`
+- `leaderboard_bbh_salient_translation_error_detection`
+- `leaderboard_bbh_snarks`
+- `leaderboard_bbh_sports_understanding`
+- `leaderboard_bbh_temporal_sequences`
+- `leaderboard_bbh_tracking_shuffled_objects_five_objects`
+- `leaderboard_bbh_tracking_shuffled_objects_seven_objects`
+- `leaderboard_bbh_tracking_shuffled_objects_three_objects`
+- `leaderboard_bbh_web_of_lies`
+- `leaderboard_bbh_word_sorting`
+
+## GPQA
+
+### Paper
+
+Title: GPQA: A Graduate-Level Google-Proof Q&A Benchmark
+
+We present GPQA, a challenging dataset of 448 multiple-choice questions written
+by domain experts in biology, physics, and chemistry. We ensure that the
+questions are high-quality and extremely difficult: experts who have or are
+pursuing PhDs in the corresponding domains reach 65% accuracy (74% when
+discounting clear mistakes the experts identified in retrospect), while highly
+skilled non-expert validators only reach 34% accuracy, despite spending on
+average over 30 minutes with unrestricted access to the web (i.e., the
+questions are “Google-proof”). The questions are also difficult for
+state-of-the-art AI systems, with our strongest GPT-4–based baseline achieving
+39% accuracy. If we are to use future AI systems to help us answer very hard
+questions—for example, when developing new scientific knowledge—we need to
+develop scalable oversight methods that enable humans to supervise their
+outputs, which may be difficult even if the supervisors are themselves skilled
+and knowledgeable. The difficulty of GPQA both for skilled non-experts and
+frontier AI systems should enable realistic scalable oversight experiments,
+which we hope can help devise ways for human experts to reliably get truthful
+information from AI systems that surpass human capabilities.
+
+- Paper: https://huggingface.co/papers/2311.12022
+- Homepage: https://github.com/idavidrein/gpqa/tree/main
+
+### Citation
+
+```
+@misc{rein2023gpqa,
+      title={GPQA: A Graduate-Level Google-Proof Q&A Benchmark},
+      author={David Rein and Betty Li Hou and Asa Cooper Stickland and Jackson Petty and Richard Yuanzhe Pang and Julien Dirani and Julian Michael and Samuel R. Bowman},
+      year={2023},
+      eprint={2311.12022},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI}
+}
+```
+
+### Groups
+
+- `leaderboard_gpqa`
+
+### Tasks
+
+- `leaderboard_gpqa_extended`
+- `leaderboard_gpqa_diamond`
+- `leaderboard_gpqa_main`
+
+## IFEval
+
+### Paper
+
+Title: Instruction-Following Evaluation for Large Language Models
+
+One core capability of Large Language Models (LLMs) is to follow natural
+language instructions. However, the evaluation of such abilities is not
+standardized: Human evaluations are expensive, slow, and not objectively
+reproducible, while LLM-based auto-evaluation is potentially biased or limited
+by the ability of the evaluator LLM. To overcome these issues, we introduce
+Instruction-Following Eval (IFEval) for large language models. IFEval is a
+straightforward and easy-to-reproduce evaluation benchmark. It focuses on a set
+of "verifiable instructions" such as "write in more than 400 words" and
+"mention the keyword of AI at least 3 times". We identified 25 types of those
+verifiable instructions and constructed around 500 prompts, with each prompt
+containing one or more verifiable instructions. We show evaluation results of
+two widely available LLMs on the market.
+
+- Paper: https://huggingface.co/papers/2210.09261
+- Homepage: https://github.com/google-research/google-research/tree/master/instruction_following_eval
+
+### Citation
+
+```
+@article{zhou2023instructionfollowing,
+  title={Instruction-Following Evaluation for Large Language Models},
+  author={Jeffrey Zhou and Tianjian Lu and Swaroop Mishra and Siddhartha Brahma and Sujoy Basu and Yi Luan and Denny Zhou and Le Hou},
+  journal={arXiv preprint arXiv:2311.07911},
+  year={2023},
+}
+```
+
+### Tasks
+
+- `leaderboard_ifeval`
+
+## MATH-hard
+
+This is the 4 shots variant of minerva math but only keeping the level 5 questions.
+
+### Paper
+
+Title: Measuring Mathematical Problem Solving With the MATH Dataset
+
+Many intellectual endeavors require mathematical problem solving, but this
+skill remains beyond the capabilities of computers. To measure this ability in
+machine learning models, we introduce MATH, a new dataset of 12,500 challenging
+competition mathematics problems. Each problem in MATH has a full step-by-step
+solution which can be used to teach models to generate answer derivations and
+explanations.
+
+NOTE: The few-shot and the generated answer extraction is based on the
+[Minerva](https://arxiv.org/abs/2206.14858) and exact match equivalence is
+calculated using the `sympy` library. This requires additional dependencies,
+which can be installed via the `lm-eval[math]` extra.
+
+- Paper: https://huggingface.co/papers/2103.03874
+- Homepage: https://github.com/hendrycks/math
+
+
+### Citation
+
+```
+@article{hendrycksmath2021,
+  title={Measuring Mathematical Problem Solving With the MATH Dataset},
+  author={Dan Hendrycks and Collin Burns and Saurav Kadavath and Akul Arora and Steven Basart and Eric Tang and Dawn Song and Jacob Steinhardt},
+  journal={NeurIPS},
+  year={2021}
+}
+@misc{2206.14858,
+Author = {Aitor Lewkowycz and Anders Andreassen and David Dohan and Ethan Dye and Henryk Michalewski and Vinay Ramasesh and Ambrose Slone and Cem Anil and Imanol Schlag and Theo Gutman-Solo and Yuhuai Wu and Behnam Neyshabur and Guy Gur-Ari and Vedant Misra},
+Title = {Solving Quantitative Reasoning Problems with Language Models},
+Year = {2022},
+Eprint = {arXiv:2206.14858},
+}
+```
+
+### Groups
+
+- `leaderboard_math_hard`
+
+### Tasks
+
+- `leaderboard_math_algebra_hard`
+- `leaderboard_math_counting_and_prob_hard`
+- `leaderboard_math_geometry_hard`
+- `leaderboard_math_intermediate_algebra_hard`
+- `leaderboard_math_num_theory_hard`
+- `leaderboard_math_prealgebra_hard`
+- `leaderboard_math_precalc_hard`
+
+
+## MMLU-Pro
+
+### Paper
+
+Title: MMLU-Pro: A More Robust and Challenging Multi-Task Language
+Understanding Benchmark
+
+In the age of large-scale language models, benchmarks like the Massive
+Multitask Language Understanding (MMLU) have been pivotal in pushing the
+boundaries of what AI can achieve in language comprehension and reasoning
+across diverse domains. However, as models continue to improve, their
+performance on these benchmarks has begun to plateau, making it increasingly
+difficult to discern differences in model capabilities. This paper introduces
+MMLU-Pro, an enhanced dataset designed to extend the mostly knowledge-driven
+MMLU benchmark by integrating more challenging, reasoning-focused questions and
+expanding the choice set from four to ten options. Additionally, MMLU-Pro
+eliminates the trivial and noisy questions in MMLU. Our experimental results
+show that MMLU-Pro not only raises the challenge, causing a significant drop in
+accuracy by 16% to 33% compared to MMLU but also demonstrates greater stability
+under varying prompts. With 24 different prompt styles tested, the sensitivity
+of model scores to prompt variations decreased from 4-5% in MMLU to just 2% in
+MMLU-Pro. Additionally, we found that models utilizing Chain of Thought (CoT)
+reasoning achieved better performance on MMLU-Pro compared to direct answering,
+which is in stark contrast to the findings on the original MMLU, indicating
+that MMLU-Pro includes more complex reasoning questions. Our assessments
+confirm that MMLU-Pro is a more discriminative benchmark to better track
+progress in the field.
+
+- Paper: https://huggingface.co/papers/2406.01574
+- Homepage: https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro
+
+### Citation
+
+```
+@misc{wang2024mmluprorobustchallengingmultitask,
+      title={MMLU-Pro: A More Robust and Challenging Multi-Task Language
+      Understanding Benchmark},
+      author={Yubo Wang and Xueguang Ma and Ge Zhang and Yuansheng Ni and Abhranil Chandra and Shiguang Guo and Weiming Ren and Aaran Arulraj and Xuan He and Ziyan Jiang and Tianle Li and Max Ku and Kai Wang and Alex Zhuang and Rongqi Fan and Xiang Yue and Wenhu Chen},
+      year={2024},
+      eprint={2406.01574},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2406.01574},
+}
+```
+
+### Groups
+
+- `leaderboard_mmlu_pro`
+
+### Tasks
+
+- `leaderboard_mmlu_pro`
+
+
+## Musr
+
+### Paper
+
+Title: MuSR: Testing the Limits of Chain-of-thought with Multistep Soft
+Reasoning  
+
+While large language models (LLMs) equipped with techniques like
+chain-of-thought prompting have demonstrated impressive capabilities, they
+still fall short in their ability to reason robustly in complex settings.
+However, evaluating LLM reasoning is challenging because system capabilities
+continue to grow while benchmark datasets for tasks like logical deduction have
+remained static. We introduce MuSR, a dataset for evaluating language models on
+multistep soft reasoning tasks specified in a natural language narrative. This
+dataset has two crucial features. First, it is created through a novel
+neurosymbolic synthetic-to-natural generation algorithm, enabling the
+construction of complex reasoning instances that challenge GPT-4 (e.g., murder
+mysteries roughly 1000 words in length) and which can be scaled further as more
+capable LLMs are released. Second, our dataset instances are free text
+narratives corresponding to real-world domains of reasoning; this makes it
+simultaneously much more challenging than other synthetically-crafted
+benchmarks while remaining realistic and tractable for human annotators to
+solve with high accuracy. We evaluate a range of LLMs and prompting techniques
+on this dataset and characterize the gaps that remain for techniques like
+chain-of-thought to perform robust reasoning.
+
+- Paper: https://huggingface.co/papers/2310.16049
+- Homepage: https://zayne-sprague.github.io/MuSR/
+
+### Citation
+
+```
+@misc{sprague2024musrtestinglimitschainofthought,
+      title={MuSR: Testing the Limits of Chain-of-thought with Multistep Soft
+      Reasoning},
+      author={Zayne Sprague and Xi Ye and Kaj Bostrom and Swarat Chaudhuri and Greg Durrett},
+      year={2024},
+      eprint={2310.16049},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2310.16049},
+}
+```
+
+### Groups
+
+- `leaderboard_musr`
+
+### Tasks
+
+- `leaderboard_musr_murder_mysteries`
+- `leaderboard_musr_object_placements`
+- `leaderboard_musr_team_allocation`

lm_eval/tasks/leaderboard/bbh_mc/_fewshot_template_yaml

+dataset_path: SaylorTwift/bbh
+output_type: multiple_choice
+test_split: test
+doc_to_text: 'Q: {{input}}
+
+  A:'
+doc_to_target: "{{target}}"
+metric_list:
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+num_fewshot: 3
+fewshot_config:
+  sampler: first_n
+metadata:
+  version: 0.0

lm_eval/tasks/leaderboard/bbh_mc/_leaderboard_bbh.yaml

+group: leaderboard_bbh
+task:
+  - leaderboard_bbh_boolean_expressions
+  - leaderboard_bbh_causal_judgement
+  - leaderboard_bbh_date_understanding
+  - leaderboard_bbh_disambiguation_qa
+  - leaderboard_bbh_formal_fallacies
+  - leaderboard_bbh_geometric_shapes
+  - leaderboard_bbh_hyperbaton
+  - leaderboard_bbh_logical_deduction_five_objects
+  - leaderboard_bbh_logical_deduction_seven_objects
+  - leaderboard_bbh_logical_deduction_three_objects
+  - leaderboard_bbh_movie_recommendation
+  - leaderboard_bbh_navigate
+  - leaderboard_bbh_object_counting
+  - leaderboard_bbh_penguins_in_a_table
+  - leaderboard_bbh_reasoning_about_colored_objects
+  - leaderboard_bbh_ruin_names
+  - leaderboard_bbh_salient_translation_error_detection
+  - leaderboard_bbh_snarks
+  - leaderboard_bbh_sports_understanding
+  - leaderboard_bbh_temporal_sequences
+  - leaderboard_bbh_tracking_shuffled_objects_five_objects
+  - leaderboard_bbh_tracking_shuffled_objects_seven_objects
+  - leaderboard_bbh_tracking_shuffled_objects_three_objects
+  - leaderboard_bbh_web_of_lies

lm_eval/tasks/leaderboard/bbh_mc/boolean_expressions.yaml

+dataset_name: boolean_expressions
+description: 'Evaluate the result of a random Boolean expression.
+
+        '
+doc_to_choice: ["False", "True"]
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: not ( ( not not True ) ) is
+    target: 'False'
+  - input: True and False and not True and True is
+    target: 'False'
+  - input: not not ( not ( False ) ) is
+    target: 'True'
+include: _fewshot_template_yaml
+task: leaderboard_bbh_boolean_expressions

lm_eval/tasks/leaderboard/bbh_mc/causal_judgement.yaml

+dataset_name: causal_judgement
+description: 'Answer questions about causal attribution.
+
+        '
+doc_to_choice: ["Yes", "No"]
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'How would a typical person answer each of the following questions about
+      causation?
+
+      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?
+
+      Options:
+
+      - Yes
+
+      - No'
+    target: 'No'
+  - input: 'How would a typical person answer each of the following questions about
+      causation?
+
+      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?
+
+      Options:
+
+      - Yes
+
+      - No'
+    target: 'Yes'
+  - input: 'How would a typical person answer each of the following questions about
+      causation?
+
+      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?
+
+      Options:
+
+      - Yes
+
+      - No'
+    target: 'Yes'
+include: _fewshot_template_yaml
+task: leaderboard_bbh_causal_judgement

lm_eval/tasks/leaderboard/bbh_mc/date_understanding.yaml

+dataset_name: date_understanding
+description: 'Infer the date from context.
+
+        '
+doc_to_choice: ["(A)", "(B)", "(C)", "(D)", "(E)", "(F)"]
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Today is Christmas Eve of 1937. What is the date 10 days ago in MM/DD/YYYY?
+
+      Options:
+
+      (A) 12/14/2026
+
+      (B) 12/14/1950
+
+      (C) 12/14/2007
+
+      (D) 12/14/1937
+
+      (E) 07/14/1938
+
+      (F) 12/14/1988'
+    target: (D)
+  - input: 'Tomorrow is 11/12/2019. What is the date one year ago from today in MM/DD/YYYY?
+
+      Options:
+
+      (A) 09/04/2018
+
+      (B) 11/11/2018
+
+      (C) 08/25/2018
+
+      (D) 11/02/2018
+
+      (E) 11/04/2018'
+    target: (B)
+  - input: 'Jane and John married on Jan 2, 1958. It is their 5-year anniversary today.
+      What is the date tomorrow in MM/DD/YYYY?
+
+      Options:
+
+      (A) 01/11/1961
+
+      (B) 01/03/1963
+
+      (C) 01/18/1961
+
+      (D) 10/14/1960
+
+      (E) 01/03/1982
+
+      (F) 12/03/1960'
+    target: (B)
+include: _fewshot_template_yaml
+task: leaderboard_bbh_date_understanding

lm_eval/tasks/leaderboard/bbh_mc/disambiguation_qa.yaml

+dataset_name: disambiguation_qa
+description: 'Clarify the meaning of sentences with ambiguous pronouns.
+
+        '
+doc_to_choice: ["(A)", "(B)", "(C)"]
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'In the following sentences, explain the antecedent of the pronoun (which
+      thing the pronoun refers to), or state that it is ambiguous.
+
+      Sentence: The chief told the counselor that they took the day off.
+
+      Options:
+
+      (A) The chief took the day off
+
+      (B) The counselor took the day off
+
+      (C) Ambiguous'
+    target: (A)
+  - input: 'In the following sentences, explain the antecedent of the pronoun (which
+      thing the pronoun refers to), or state that it is ambiguous.
+
+      Sentence: The manager sent a message to the secretary, but he didn''t reply
+      yet.
+
+      Options:
+
+      (A) The secretary didn''t reply yet
+
+      (B) The manager didn''t reply yet
+
+      (C) Ambiguous'
+    target: (A)
+  - input: 'In the following sentences, explain the antecedent of the pronoun (which
+      thing the pronoun refers to), or state that it is ambiguous.
+
+      Sentence: Bailey will plan to meet the director at his office
+
+      Options:
+
+      (A) It will be Bailey''s office
+
+      (B) It will be the director''s office
+
+      (C) Ambiguous'
+    target: (C)
+include: _fewshot_template_yaml
+task: leaderboard_bbh_disambiguation_qa

lm_eval/tasks/leaderboard/bbh_mc/formal_fallacies.yaml

+dataset_name: formal_fallacies
+description: 'Distinguish deductively valid arguments from formal fallacies.
+
+        '
+doc_to_choice: ["valid", "invalid"]
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: '"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."
+
+      Is the argument, given the explicitly stated premises, deductively valid or
+      invalid?
+
+      Options:
+
+      - valid
+
+      - invalid'
+    target: valid
+  - input: '"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."
+
+      Is the argument, given the explicitly stated premises, deductively valid or
+      invalid?
+
+      Options:
+
+      - valid
+
+      - invalid'
+    target: valid
+  - input: '"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."
+
+      Is the argument, given the explicitly stated premises, deductively valid or
+      invalid?
+
+      Options:
+
+      - valid
+
+      - invalid'
+    target: invalid
+include: _fewshot_template_yaml
+task: leaderboard_bbh_formal_fallacies

lm_eval/tasks/leaderboard/bbh_mc/geometric_shapes.yaml

+dataset_name: geometric_shapes
+description: 'Name geometric shapes from their SVG paths.
+
+        '
+doc_to_choice: ["(A)","(B)","(C)","(D)","(E)","(F)","(G)","(H)","(I)","(J)","(K)"]
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: '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
+
+      Options:
+
+      (A) circle
+
+      (B) heptagon
+
+      (C) hexagon
+
+      (D) kite
+
+      (E) line
+
+      (F) octagon
+
+      (G) pentagon
+
+      (H) rectangle
+
+      (I) sector
+
+      (J) triangle'
+    target: (F)
+  - input: '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
+
+      Options:
+
+      (A) circle
+
+      (B) heptagon
+
+      (C) hexagon
+
+      (D) kite
+
+      (E) line
+
+      (F) octagon
+
+      (G) pentagon
+
+      (H) rectangle
+
+      (I) sector
+
+      (J) triangle'
+    target: (G)
+  - input: '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
+
+      Options:
+
+      (A) circle
+
+      (B) heptagon
+
+      (C) hexagon
+
+      (D) kite
+
+      (E) line
+
+      (F) octagon
+
+      (G) pentagon
+
+      (H) rectangle
+
+      (I) sector
+
+      (J) triangle'
+    target: (D)
+include: _fewshot_template_yaml
+task: leaderboard_bbh_geometric_shapes

lm_eval/tasks/leaderboard/bbh_mc/hyperbaton.yaml

+dataset_name: hyperbaton
+description: 'Order adjectives correctly in English sentences.
+
+        '
+doc_to_choice: ["(A)", "(B)"]
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: 'Which sentence has the correct adjective order:
+
+      Options:
+
+      (A) rubber terrible ship
+
+      (B) terrible rubber ship'
+    target: (B)
+  - input: 'Which sentence has the correct adjective order:
+
+      Options:
+
+      (A) repulsive small Brazilian exercise ship
+
+      (B) Brazilian repulsive exercise small ship'
+    target: (A)
+  - input: 'Which sentence has the correct adjective order:
+
+      Options:
+
+      (A) blue gold wonderful square shoe
+
+      (B) wonderful square blue gold shoe'
+    target: (B)
+include: _fewshot_template_yaml
+task: leaderboard_bbh_hyperbaton

lm_eval/tasks/leaderboard/bbh_mc/logical_deduction_five_objects.yaml

+dataset_name: logical_deduction_five_objects
+description: 'A logical deduction task which requires deducing the order of a sequence
+  of objects.
+
+        '
+doc_to_choice: ["(A)","(B)","(C)","(D)","(E)"]
+fewshot_config:
+  sampler: first_n
+  samples:
+  - input: '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.
+
+      Options:
+
+      (A) Amy finished last
+
+      (B) Eli finished last
+
+      (C) Eve finished last'
+    target: (B)
+  - input: '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.
+
+      Options:
+
+      (A) The white book is the leftmost
+
+      (B) The green book is the leftmost
+
+      (C) The orange book is the leftmost'
+    target: (A)
+  - input: '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.
+
+      Options:
+
+      (A) The red book is the leftmost
+
+      (B) The gray book is the leftmost
+
+      (C) The white book is the leftmost'
+    target: (C)
+include: _fewshot_template_yaml
+task: leaderboard_bbh_logical_deduction_five_objects