{"url":"/task/logical-fallacies","name":"Logical Fallacies","slug":"logical-fallacies","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":34,"papers_with_code":14,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/logical-fallacies-on-big-bench","slug":"logical-fallacies-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":1,"metrics":["Accuracy "],"first_row_in_archive_order":{"model":"Gopher-280B (few-shot, k=5)","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","paper_url":"/paper/scaling-language-models-methods-analysis-1","paper_date":"2021-12-08","arxiv_id":"2112.11446","code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}],"syntology":null}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349},{"url":"/dataset/justlogic","name":"JustLogic","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":14,"of":14,"tagged_in_all":34,"items":[{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/logical-fallacy-detection","title":"Logical Fallacy Detection","date":"2022-02-28","arxiv_id":"2202.13758","repositories_listed":2,"syntology":null},{"url":"/paper/leveraging-context-for-multimodal-fallacy","title":"Leveraging Context for Multimodal Fallacy Classification in Political Debates","date":"2025-07-21","arxiv_id":"2507.15641","repositories_listed":1,"syntology":null},{"url":"/paper/socrates-or-smartypants-testing-logic","title":"Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-based Test Oracles","date":"2025-04-09","arxiv_id":"2504.12312","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-better-logical","title":"Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation","date":"2025-03-30","arxiv_id":"2503.23363","repositories_listed":1,"syntology":null},{"url":"/paper/ruozhibench-evaluating-llms-with-logical","title":"RuozhiBench: Evaluating LLMs with Logical Fallacies and Misleading Premises","date":"2025-02-18","arxiv_id":"2502.13125","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-logical-fallacy-reasoning-in-llms","title":"Boosting Logical Fallacy Reasoning in LLMs via Logical Structure Tree","date":"2024-10-15","arxiv_id":"2410.12048","repositories_listed":1,"syntology":null},{"url":"/paper/grounding-fallacies-misrepresenting","title":"Grounding Fallacies Misrepresenting Scientific Publications in Evidence","date":"2024-08-23","arxiv_id":"2408.12812","repositories_listed":1,"syntology":null},{"url":"/paper/a-logical-fallacy-informed-framework-for","title":"A Logical Fallacy-Informed Framework for Argument Generation","date":"2024-08-07","arxiv_id":"2408.03618","repositories_listed":1,"syntology":null},{"url":"/paper/olympiadbench-a-challenging-benchmark-for","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","date":"2024-02-21","arxiv_id":"2402.14008","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/a-closer-look-at-the-self-verification","title":"A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning","date":"2023-11-14","arxiv_id":"2311.07954","repositories_listed":1,"syntology":null},{"url":"/paper/how-susceptible-are-llms-to-logical-fallacies","title":"How susceptible are LLMs to Logical Fallacies?","date":"2023-08-18","arxiv_id":"2308.09853","repositories_listed":1,"syntology":null},{"url":"/paper/case-based-reasoning-with-language-models-for","title":"Case-Based Reasoning with Language Models for Classification of Logical Fallacies","date":"2023-01-27","arxiv_id":"2301.11879","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/robust-and-explainable-identification-of","title":"Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments","date":"2022-12-12","arxiv_id":"2212.07425","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}