{"url":"/dataset/justlogic","name":"JustLogic","full_name":null,"description_markdown":"JustLogic is a natural language deductive reasoning dataset. JustLogic is (i) highly complex, capable of generating a diverse range of linguistic patterns, vocabulary, and argument structures; (ii) prior knowledge independent, eliminating the advantage of models possessing prior knowledge and ensuring that only deductive reasoning is used to answer questions; and (iii) capable of in-depth error analysis on the heterogeneous effects of reasoning depth and argument form on model accuracy.","description_withheld":null,"homepage":"https://github.com/michaelchen-lab/JustLogic","introduced_date":"2025-01-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/justlogic-a-comprehensive-benchmark-for","title":"JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models","first_author":"Michael K. Chen","url":null},"license":{"name":"CC BY","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Logical Reasoning","url":"/task/logical-reasoning","datasets_with_task":"/datasets/task/logical-reasoning"},{"name":"Reasoning Chain Explanations","url":"/task/reasoning-chain-explanations","datasets_with_task":"/datasets/task/reasoning-chain-explanations"},{"name":"Logical Reasoning Question Answering","url":"/task/logical-reasoning-question-ansering","datasets_with_task":"/datasets/task/logical-reasoning-question-ansering"},{"name":"Logical Fallacies","url":"/task/logical-fallacies","datasets_with_task":"/datasets/task/logical-fallacies"},{"name":"Logical Reasoning Reading Comprehension","url":"/task/logical-reasoning-reading-comprehension","datasets_with_task":"/datasets/task/logical-reasoning-reading-comprehension"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["JustLogic"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}