{"url":"/task/fact-verification","name":"Fact Verification","slug":"fact-verification","description_markdown":"Fact verification, also called \"fact checking\", is a process of verifying facts in natural text against a database of facts.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":216,"papers_with_code":129,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":17,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/fact-verification-on-kilt-fever","slug":"fact-verification-on-kilt-fever","dataset":"KILT: FEVER","dataset_url":"/dataset/kilt","rows_in_archive":33,"metrics":["KILT-AC","R-Prec","Recall@5","Accuracy"],"first_row_in_archive_order":{"model":"Re2G","paper_title":"Re2G: Retrieve, Rerank, Generate","paper_url":"/paper/re2g-retrieve-rerank-generate-2","paper_date":"2022-07-13","arxiv_id":"2207.06300","code_links":[{"title":"ibm/kgi-slot-filling","url":"https://github.com/ibm/kgi-slot-filling"}],"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}}},{"leaderboard":"/sota/fact-verification-on-fever","slug":"fact-verification-on-fever","dataset":"FEVER","dataset_url":"/dataset/fever","rows_in_archive":7,"metrics":["Accuracy","FEVER"],"first_row_in_archive_order":{"model":"ProoFVer-SB","paper_title":"ProoFVer: Natural Logic Theorem Proving for Fact Verification","paper_url":"/paper/proofver-natural-logic-theorem-proving-for","paper_date":"2021-08-25","arxiv_id":"2108.11357","code_links":[{"title":"krishnamrith12/proofver","url":"https://github.com/krishnamrith12/proofver"}],"syntology":null}},{"leaderboard":"/sota/fact-verification-on-danfever","slug":"fact-verification-on-danfever","dataset":"DanFEVER","dataset_url":"/dataset/danfever","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"DanFEVER XLM-RoBERTa Large","paper_title":"DanFEVER: claim verification dataset for Danish","paper_url":"/paper/danfever-claim-verification-dataset-for","paper_date":"","arxiv_id":null,"code_links":[{"title":"StrombergNLP/danfever","url":"https://github.com/StrombergNLP/danfever"}],"syntology":null}}],"datasets":[{"url":"/dataset/fever","name":"FEVER","full_name":"Fact Extraction and VERification","num_papers_in_archive":498},{"url":"/dataset/kilt","name":"KILT","full_name":"KILT Benchmark","num_papers_in_archive":117},{"url":"/dataset/feverous","name":"FEVEROUS","full_name":"Fact Extraction and VERification Over Unstructured and Structured information","num_papers_in_archive":46},{"url":"/dataset/vitaminc","name":"VitaminC","full_name":"Fact Verification with Contrastive Evidence","num_papers_in_archive":42},{"url":"/dataset/hover","name":"HoVer","full_name":"","num_papers_in_archive":35},{"url":"/dataset/creak","name":"CREAK","full_name":"","num_papers_in_archive":30},{"url":"/dataset/snopes","name":"Snopes","full_name":"","num_papers_in_archive":22},{"url":"/dataset/politifact","name":"PolitiFact","full_name":"","num_papers_in_archive":20},{"url":"/dataset/averitec","name":"AVeriTeC","full_name":"AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web","num_papers_in_archive":17},{"url":"/dataset/x-fact","name":"X-Fact","full_name":"","num_papers_in_archive":16},{"url":"/dataset/faviq","name":"FaVIQ","full_name":"Fact Verification from Information-seeking Questions","num_papers_in_archive":15},{"url":"/dataset/mocheg","name":"Mocheg","full_name":"","num_papers_in_archive":10},{"url":"/dataset/factify","name":"FACTIFY","full_name":"a dataset on multi-modal fact verification","num_papers_in_archive":4},{"url":"/dataset/liar2","name":"LIAR2","full_name":"","num_papers_in_archive":4},{"url":"/dataset/danfever","name":"DanFEVER","full_name":"","num_papers_in_archive":3},{"url":"/dataset/cfever","name":"CFEVER","full_name":"","num_papers_in_archive":1},{"url":"/dataset/evidence-based-factual-error-correction","name":"Evidence-based Factual Error Correction","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":30,"of":129,"tagged_in_all":216,"items":[{"url":"/paper/retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","repositories_listed":18,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/react-synergizing-reasoning-and-acting-in","title":"ReAct: Synergizing Reasoning and Acting in Language Models","date":"2022-10-06","arxiv_id":"2210.03629","repositories_listed":9,"syntology":{"n":34,"n_ran":15,"n_unverified":19,"n_pointer_only":5}},{"url":"/paper/self-rag-learning-to-retrieve-generate-and","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","date":"2023-10-17","arxiv_id":"2310.11511","repositories_listed":6,"syntology":{"n":14,"n_ran":8,"n_unverified":6,"n_pointer_only":3}},{"url":"/paper/precise-zero-shot-dense-retrieval-without","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","date":"2022-12-20","arxiv_id":"2212.10496","repositories_listed":3,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/factual-error-correction-of-claims","title":"Evidence-based Factual Error Correction","date":"2020-12-31","arxiv_id":"2012.15788","repositories_listed":3,"syntology":null},{"url":"/paper/kilt-a-benchmark-for-knowledge-intensive","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","date":"2020-09-04","arxiv_id":"2009.02252","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/towards-debiasing-fact-verification-models","title":"Towards Debiasing Fact Verification Models","date":"2019-08-14","arxiv_id":"1908.05267","repositories_listed":3,"syntology":null},{"url":"/paper/benchmarking-retrieval-augmented-generation-1","title":"Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts","date":"2025-02-24","arxiv_id":"2502.17297","repositories_listed":2,"syntology":null},{"url":"/paper/cfever-a-chinese-fact-extraction-and","title":"CFEVER: A Chinese Fact Extraction and VERification Dataset","date":"2024-02-20","arxiv_id":"2402.13025","repositories_listed":2,"syntology":null},{"url":"/paper/chain-of-table-evolving-tables-in-the","title":"Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding","date":"2024-01-09","arxiv_id":"2401.04398","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/learning-to-filter-context-for-retrieval","title":"Learning to Filter Context for Retrieval-Augmented Generation","date":"2023-11-14","arxiv_id":"2311.08377","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/alignscore-evaluating-factual-consistency","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","date":"2023-05-26","arxiv_id":"2305.16739","repositories_listed":2,"syntology":null},{"url":"/paper/toward-a-unified-framework-for-unsupervised","title":"Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework","date":"2022-12-20","arxiv_id":"2212.10097","repositories_listed":2,"syntology":{"n":20,"n_ran":0,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/decorrelate-irrelevant-purify-relevant","title":"Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective","date":"2022-02-16","arxiv_id":"2202.08048","repositories_listed":2,"syntology":null},{"url":"/paper/creak-a-dataset-for-commonsense-reasoning","title":"CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge","date":"2021-09-03","arxiv_id":"2109.01653","repositories_listed":2,"syntology":null},{"url":"/paper/faviq-fact-verification-from-information","title":"FaVIQ: FAct Verification from Information-seeking Questions","date":"2021-07-05","arxiv_id":"2107.02153","repositories_listed":2,"syntology":null},{"url":"/paper/multilingual-evidence-retrieval-and-fact","title":"Multilingual Evidence Retrieval and Fact Verification to Combat Global Disinformation: The Power of Polyglotism","date":"2020-12-16","arxiv_id":"2012.08919","repositories_listed":2,"syntology":null},{"url":"/paper/where-are-the-facts-searching-for-fact","title":"Where Are the Facts? Searching for Fact-checked Information to Alleviate the Spread of Fake News","date":"2020-10-07","arxiv_id":"2010.03159","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/revealing-the-importance-of-semantic","title":"Revealing the Importance of Semantic Retrieval for Machine Reading at Scale","date":"2019-09-17","arxiv_id":"1909.08041","repositories_listed":2,"syntology":{"n":17,"n_ran":6,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/simple-but-effective-techniques-to-reduce","title":"End-to-End Bias Mitigation by Modelling Biases in Corpora","date":"2019-09-13","arxiv_id":"1909.06321","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/gear-graph-based-evidence-aggregating-and-1","title":"GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification","date":"2019-07-22","arxiv_id":"1908.01843","repositories_listed":2,"syntology":null},{"url":"/paper/combining-fact-extraction-and-verification","title":"Combining Fact Extraction and Verification with Neural Semantic Matching Networks","date":"2018-11-16","arxiv_id":"1811.07039","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/ds-gt-at-checkthat-2025-evaluating-context","title":"DS@GT at CheckThat! 2025: Evaluating Context and Tokenization Strategies for Numerical Fact Verification","date":"2025-07-08","arxiv_id":"2507.06195","repositories_listed":1,"syntology":null},{"url":"/paper/verifying-the-verifiers-unveiling-pitfalls","title":"Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers","date":"2025-06-16","arxiv_id":"2506.13342","repositories_listed":1,"syntology":null},{"url":"/paper/climateviz-a-benchmark-for-statistical","title":"ClimateViz: A Benchmark for Statistical Reasoning and Fact Verification on Scientific Charts","date":"2025-06-10","arxiv_id":"2506.08700","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-table-exploring-reinforcement","title":"Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning","date":"2025-06-02","arxiv_id":"2506.01710","repositories_listed":1,"syntology":null},{"url":"/paper/table-r1-inference-time-scaling-for-table","title":"Table-R1: Inference-Time Scaling for Table Reasoning","date":"2025-05-29","arxiv_id":"2505.23621","repositories_listed":1,"syntology":null},{"url":"/paper/2503-00955","title":"SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking","date":"2025-03-02","arxiv_id":"2503.00955","repositories_listed":1,"syntology":null},{"url":"/paper/hippo-enhancing-the-table-understanding","title":"HIPPO: Enhancing the Table Understanding Capability of Large Language Models through Hybrid-Modal Preference Optimization","date":"2025-02-24","arxiv_id":"2502.17315","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/step-by-step-fact-verification-system-for","title":"Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning","date":"2025-02-20","arxiv_id":"2502.14765","repositories_listed":1,"syntology":null}],"syntology_records":13,"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"}}