{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":34,"of":34,"of_with_code":14,"tagged_in_all":34,"counts":{"archive_papers_tagged":34,"with_a_code_link":14,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":34,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/scaling-language-models-methods-analysis-1","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/olympiadbench-a-challenging-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2402.14008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14008"}},"official":{"repos":["openbmb/olympiadbench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-closer-look-at-the-self-verification","slug":"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","slug":"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","slug":"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_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/case-based-reasoning-with-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2301.11879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11879"}},"official":{"repos":["zhpinkman/cbr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-and-explainable-identification-of","slug":"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},{"url":null,"slug":"are-large-language-models-good-at-detecting","title":"Are Large Language Models Good at Detecting Propaganda?","date":"2025-05-19","arxiv_id":"2505.13706","repositories_listed":0,"syntology":null},{"url":null,"slug":"slurg-investigating-the-feasibility-of","title":"SLURG: Investigating the Feasibility of Generating Synthetic Online Fallacious Discourse","date":"2025-04-16","arxiv_id":"2504.12466","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-automatic-credibility-assessment","title":"A Survey on Automatic Credibility Assessment of Textual Credibility Signals in the Era of Large Language Models","date":"2024-10-28","arxiv_id":"2410.21360","repositories_listed":0,"syntology":null},{"url":null,"slug":"conceptagent-llm-driven-precondition","title":"ConceptAgent: LLM-Driven Precondition Grounding and Tree Search for Robust Task Planning and Execution","date":"2024-10-08","arxiv_id":"2410.06108","repositories_listed":0,"syntology":null},{"url":null,"slug":"cocolofa-a-dataset-of-news-comments-with","title":"CoCoLoFa: A Dataset of News Comments with Common Logical Fallacies Written by LLM-Assisted Crowds","date":"2024-10-04","arxiv_id":"2410.03457","repositories_listed":0,"syntology":null},{"url":null,"slug":"flee-the-flaw-annotating-the-underlying-logic","title":"Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling","date":"2024-06-18","arxiv_id":"2406.12402","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-a-hallucinating-model-help-in-reducing","title":"Can a Hallucinating Model help in Reducing Human \"Hallucination\"?","date":"2024-05-01","arxiv_id":"2405.00843","repositories_listed":0,"syntology":null},{"url":null,"slug":"nl2fol-translating-natural-language-to-first","title":"Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detection","date":"2024-04-18","arxiv_id":"2405.02318","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-an-llm-in-identifying-logical","title":"Evaluation of an LLM in Identifying Logical Fallacies: A Call for Rigor When Adopting LLMs in HCI Research","date":"2024-04-08","arxiv_id":"2404.05213","repositories_listed":0,"syntology":null},{"url":null,"slug":"reason-from-fallacy-enhancing-large-language","title":"Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding","date":"2024-04-04","arxiv_id":"2404.04293","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-conditional-reasoning-in-answer-set","title":"Human Conditional Reasoning in Answer Set Programming","date":"2023-11-08","arxiv_id":"2311.04412","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-comparison-of-syllogistic","title":"A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models","date":"2023-11-01","arxiv_id":"2311.00445","repositories_listed":0,"syntology":null},{"url":null,"slug":"which-spurious-correlations-impact-reasoning","title":"Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals","date":"2023-06-21","arxiv_id":"2306.12146","repositories_listed":0,"syntology":null},{"url":null,"slug":"tweetspin-fine-grained-propaganda-detection","title":"TWEETSPIN: Fine-grained Propaganda Detection in Social Media Using Multi-View Representations","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-search-for-agreement-on-logical-fallacy","title":"The Search for Agreement on Logical Fallacy Annotation of an Infodemic","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dont-discuss-investigating-semantic-and","title":"“Don’t discuss”: Investigating Semantic and Argumentative Features for Supervised Propagandist Message Detection and Classification","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-propaganda-using-logistic","title":"Detection of Propaganda Using Logistic Regression","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"justdeep-at-nlp4if-2019-task-1-propaganda","title":"JUSTDeep at NLP4IF 2019 Task 1: Propaganda Detection using Ensemble Deep Learning Models","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robots-sense-making-of-fallacies-and","title":"A robot's sense-making of fallacies and rhetorical tropes. Creating ontologies of what humans try to say","date":"2019-06-24","arxiv_id":"1906.09689","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-link-between-logical-fallacies","title":"Unveiling the link between logical fallacies and web persuasion","date":"2013-04-14","arxiv_id":"1304.3940","repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/logical-fallacies/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/logical-fallacies/papers/ran/1","json":"/task/logical-fallacies/papers/ran/1.json","rows":2}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"b268004263a2b7c2362c3b94c2d3d4bb1d704956ac2890b09d8a21c322cbfb72","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}