{"url":"/dataset/fever","name":"FEVER","full_name":"Fact Extraction and VERification","description_markdown":"FEVER is a publicly available dataset for fact extraction and verification against textual sources.\r\n\r\nIt consists of 185,445 claims manually verified against the introductory sections of Wikipedia pages and classified as SUPPORTED, REFUTED or NOTENOUGHINFO. For the first two classes, systems and annotators need to also return the combination of sentences forming the necessary evidence supporting or refuting the claim.\r\n\r\nThe claims were generated by human annotators extracting claims from Wikipedia and mutating them in a variety of ways, some of which were meaning-altering. The verification of each claim was conducted in a separate annotation process by annotators who were aware of the page but not the sentence from which original claim was\r\nextracted and thus in 31.75% of the claims more than one sentence was considered appropriate evidence. Claims require composition of evidence from multiple sentences in 16.82% of cases. Furthermore, in 12.15% of the claims, this evidence was taken from multiple pages.\r\n\r\nSource: [FEVER: a large-scale dataset for Fact Extraction and VERification](https://arxiv.org/pdf/1803.05355v3.pdf)","description_withheld":null,"homepage":"https://fever.ai/resources.html","introduced_date":"2018-03-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/fever-a-large-scale-dataset-for-fact","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","first_author":"James Thorne","url":null},"license":{"name":"Custom","url":"https://s3-eu-west-1.amazonaws.com/fever.public/license.html"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Zero-shot Text Search","url":"/task/zero-shot-text-search","datasets_with_task":"/datasets/task/zero-shot-text-search"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Fact Verification","url":"/task/fact-verification","datasets_with_task":"/datasets/task/fact-verification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["FEVER"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fever","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/copenlu/fever_gold_evidence","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/fever","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/fever-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/climate-fever-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/climate-evidence-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/fever-claim-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/climate-claim-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/fever-evidence-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/EleutherAI/fever","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fever/fever","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":498,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-fever","task":"Question Answering","dataset_variant":"FEVER","rows":8,"metrics":["EM"],"first_row_in_archive_order":{"model":"CoA","paper":"/paper/chain-of-action-faithful-and-multimodal","metrics":{"EM":"68.9"},"code_links":[{"title":"MAGICS-LAB/Chain-of-Actions","url":"https://github.com/MAGICS-LAB/Chain-of-Actions"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fact-verification-on-fever","task":"Fact Verification","dataset_variant":"FEVER","rows":7,"metrics":["Accuracy","FEVER"],"first_row_in_archive_order":{"model":"ProoFVer-SB","paper":"/paper/proofver-natural-logic-theorem-proving-for","metrics":{"Accuracy":"79.47","FEVER":"76.82"},"code_links":[{"title":"krishnamrith12/proofver","url":"https://github.com/krishnamrith12/proofver"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-retrieval-on-fever","task":"Text Retrieval","dataset_variant":"FEVER","rows":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","metrics":{"nDCG@10":"63.8"},"code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":22,"samples_ran":10,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/chain-of-action-faithful-and-multimodal","title":"Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models","date":"2024-03-26","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":8,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dspy-compiling-declarative-language-model","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","date":"2023-10-05","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/measuring-and-narrowing-the-compositionality","title":"Measuring and Narrowing the Compositionality Gap in Language Models","date":"2022-10-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/paragraph-based-transformer-pre-training-for","title":"Paragraph-based Transformer Pre-training for Multi-Sentence Inference","date":"2022-05-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/proofver-natural-logic-theorem-proving-for","title":"ProoFVer: Natural Logic Theorem Proving for Fact Verification","date":"2021-08-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/kernel-graph-attention-network-for-fact","title":"Fine-grained Fact Verification with Kernel Graph Attention Network","date":"2019-10-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reasoning-over-semantic-level-graph-for-fact","title":"Reasoning Over Semantic-Level Graph for Fact Checking","date":"2019-09-09","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gear-graph-based-evidence-aggregating-and-1","title":"GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification","date":"2019-07-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","rows_on_this_dataset":1,"code_links":21,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":50,"samples_ran":29,"samples_unverified":21,"pointer_only_for_licence":3,"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."}