{"url":"/task/formal-logic","name":"Formal Logic","slug":"formal-logic","description_markdown":null,"categories":[{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":73,"papers_with_code":20,"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":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/formal-logic-on-big-bench","slug":"formal-logic-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/mindgames","name":"Mindgames","full_name":"","num_papers_in_archive":4},{"url":"/dataset/probability-words-nli-1","name":"probability_words_nli","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/mathematical-reasoning","name":"Mathematical Reasoning"}],"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":20,"of":20,"tagged_in_all":73,"items":[{"url":"/paper/learning-deductive-reasoning-from-synthetic","title":"Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic","date":"2023-08-11","arxiv_id":"2308.07336","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"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/enhancing-reasoning-capabilities-of-llms-via","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","date":"2024-11-19","arxiv_id":"2411.12498","repositories_listed":2,"syntology":null},{"url":"/paper/learning-symbolic-rules-for-reasoning-in-1","title":"Learning Symbolic Rules for Reasoning in Quasi-Natural Language","date":"2021-11-23","arxiv_id":"2111.12038","repositories_listed":2,"syntology":null},{"url":"/paper/are-llms-reliable-translators-of-logical","title":"Are LLMs Reliable Translators of Logical Reasoning Across Lexically Diversified Contexts?","date":"2025-06-05","arxiv_id":"2506.04575","repositories_listed":1,"syntology":null},{"url":"/paper/training-step-level-reasoning-verifiers-with","title":"Training Step-Level Reasoning Verifiers with Formal Verification Tools","date":"2025-05-21","arxiv_id":"2505.15960","repositories_listed":1,"syntology":null},{"url":"/paper/cot-tl-low-resource-temporal-knowledge","title":"CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning","date":"2024-10-21","arxiv_id":"2410.16207","repositories_listed":1,"syntology":null},{"url":"/paper/autoformalization-of-game-descriptions-using","title":"Autoformalization of Game Descriptions using Large Language Models","date":"2024-09-18","arxiv_id":"2409.12300","repositories_listed":1,"syntology":null},{"url":"/paper/logic-enhanced-language-model-agents-for","title":"Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents","date":"2024-08-28","arxiv_id":"2408.16081","repositories_listed":1,"syntology":null},{"url":"/paper/ai-driven-statutory-reasoning-via-software","title":"Software Engineering Methods For AI-Driven Deductive Legal Reasoning","date":"2024-04-15","arxiv_id":"2404.09868","repositories_listed":1,"syntology":null},{"url":"/paper/realcqa-scientific-chart-question-answering","title":"RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic","date":"2023-08-03","arxiv_id":"2308.01979","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-to-generate","title":"Leveraging Large Language Models to Generate Answer Set Programs","date":"2023-07-15","arxiv_id":"2307.07699","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/harnessing-the-power-of-large-language-models","title":"Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation","date":"2023-05-24","arxiv_id":"2305.15541","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/nanopublication-based-semantic-publishing-and","title":"Nanopublication-Based Semantic Publishing and Reviewing: A Field Study with Formalization Papers","date":"2022-03-03","arxiv_id":"2203.01608","repositories_listed":1,"syntology":null},{"url":"/paper/design-of-quantum-optical-experiments-with","title":"Design of quantum optical experiments with logic artificial intelligence","date":"2021-09-27","arxiv_id":"2109.13273","repositories_listed":1,"syntology":null},{"url":"/paper/satisfiability-and-containment-of-recursive","title":"Satisfiability and Containment of Recursive SHACL","date":"2021-08-30","arxiv_id":"2108.13063","repositories_listed":1,"syntology":null},{"url":"/paper/negation-in-cognitive-reasoning","title":"Negation in Cognitive Reasoning","date":"2020-12-23","arxiv_id":"2012.12641","repositories_listed":1,"syntology":null},{"url":"/paper/bits-and-pieces-understanding-information","title":"Bits and Pieces: Understanding Information Decomposition from Part-whole Relationships and Formal Logic","date":"2020-08-21","arxiv_id":"2008.09535","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-rust-types-for-modular","title":"Leveraging Rust types for modular specification and verification","date":"2019-10-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/lectures-on-jacques-herbrand-as-a-logician","title":"Lectures on Jacques Herbrand as a Logician","date":"2009-02-26","arxiv_id":"0902.4682","repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}