{"url":"/dataset/logiqa","name":"LogiQA","full_name":null,"description_markdown":"LogiQA consists of 8,678 QA instances, covering multiple types of deductive reasoning. Results show that state-of-the-art neural models perform by far worse than human ceiling. The dataset can also serve as a benchmark for reinvestigating logical AI under the deep learning NLP setting.\r\n\r\nSource: [LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning](/paper/logiqa-a-challenge-dataset-for-machine)\r\nImage Source: [https://arxiv.org/pdf/2007.08124v1.pdf](https://arxiv.org/pdf/2007.08124v1.pdf)","description_withheld":null,"homepage":"https://github.com/lgw863/LogiQA-dataset","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/logiqa-a-challenge-dataset-for-machine","title":"LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning","first_author":"Jian Liu","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"},{"name":"Machine Reading Comprehension","url":"/task/machine-reading-comprehension","datasets_with_task":"/datasets/task/machine-reading-comprehension"},{"name":"Decision Making","url":"/task/decision-making","datasets_with_task":"/datasets/task/decision-making"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["LogiQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/jiacheng-ye/logiqa-zh","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lucasmccabe/logiqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/lgw863/LogiQA-dataset","url":"https://github.com/lgw863/LogiQA-dataset","frameworks":[]}],"num_papers_in_archive":127,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-generation-on-logiqa","task":"Text Generation","dataset_variant":"LogiQA","rows":0,"metrics":["acc"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"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."}