{"url":"/sota/table-based-fact-verification-on-tabfact","task":{"name":"Table-based Fact Verification","url":"/task/table-based-fact-verification","note":null},"dataset":{"name":"TabFact","url":"/dataset/tabfact"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Verifying facts given semi-structured data.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Test","Val"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Test":null,"Val":null}},"counts":{"rows":15,"rows_with_code":13,"rows_with_paper_page":15,"rows_dated":15,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ARTEMIS-DA","metrics":{"Test":"93.1"},"uses_additional_data":false,"paper_date":"2024-12-18","paper":"/paper/advanced-reasoning-and-transformation-engine","paper_url":"https://arxiv.org/abs/2412.14146v3","paper_title":"ARTEMIS-DA: An Advanced Reasoning and Transformation Engine for Multi-Step Insight Synthesis in Data Analytics","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Dater","metrics":{"Test":"93.0"},"uses_additional_data":false,"paper_date":"2023-01-31","paper":"/paper/large-language-models-are-versatile","paper_url":"https://arxiv.org/abs/2301.13808v3","paper_title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","code":"https://github.com/alibabaresearch/damo-convai","n_code_links":2,"syntology":null},{"rank_in_archive_order":3,"model":"PASTA","metrics":{"Test":"89.3","Val":"89.2"},"uses_additional_data":false,"paper_date":"2022-11-05","paper":"/paper/pasta-table-operations-aware-fact","paper_url":"https://arxiv.org/abs/2211.02816v1","paper_title":"PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training","code":"https://github.com/ruc-datalab/PASTA","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Chain-of-Table","metrics":{"Test":"86.61","Val":"-"},"uses_additional_data":false,"paper_date":"2024-01-09","paper":"/paper/chain-of-table-evolving-tables-in-the","paper_url":"https://arxiv.org/abs/2401.04398v2","paper_title":"Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding","code":"https://github.com/cyqiq/multicot","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"Binder","metrics":{"Test":"86.0","Val":"-"},"uses_additional_data":false,"paper_date":"2022-10-06","paper":"/paper/binding-language-models-in-symbolic-languages","paper_url":"https://arxiv.org/abs/2210.02875v2","paper_title":"Binding Language Models in Symbolic Languages","code":"https://github.com/xlang-ai/binder","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"Tab-PoT","metrics":{"Test":"85.77"},"uses_additional_data":false,"paper_date":"2024-06-14","paper":"/paper/efficient-prompting-for-llm-based-generative","paper_url":"https://arxiv.org/abs/2406.10382v3","paper_title":"Efficient Prompting for LLM-based Generative Internet of Things","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"ReasTAP-Large","metrics":{"Test":"84.9","Val":"84.6"},"uses_additional_data":false,"paper_date":"2022-10-22","paper":"/paper/reastap-injecting-table-reasoning-skills","paper_url":"https://arxiv.org/abs/2210.12374v1","paper_title":"ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples","code":"https://github.com/yale-lily/reastap","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":11,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"TAPEX-Large","metrics":{"Test":"84.2","Val":"84.6"},"uses_additional_data":false,"paper_date":"2021-07-16","paper":"/paper/tapex-table-pre-training-via-learning-a","paper_url":"https://arxiv.org/abs/2107.07653v3","paper_title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","code":"https://github.com/microsoft/Table-Pretraining","n_code_links":4,"syntology":null},{"rank_in_archive_order":9,"model":"T5-3b(UnifiedSKG)","metrics":{"Test":"83.68","Val":"83.97"},"uses_additional_data":false,"paper_date":"2022-01-16","paper":"/paper/unifiedskg-unifying-and-multi-tasking","paper_url":"https://arxiv.org/abs/2201.05966v3","paper_title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","code":"https://github.com/hkunlp/unifiedskg","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"Salience-aware TAPAS","metrics":{"Test":"82.1","Val":"82.7"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/table-based-fact-verification-with-salience","paper_url":"https://arxiv.org/abs/2109.04053v1","paper_title":"Table-based Fact Verification with Salience-aware Learning","code":"https://github.com/luka-group/salience-aware-learning","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"TAPAS-Large classifier with Counterfactual + Synthetic pre-training","metrics":{"Test":"81.0","Val":"81.0"},"uses_additional_data":false,"paper_date":"2020-10-01","paper":"/paper/understanding-tables-with-intermediate-pre","paper_url":"https://arxiv.org/abs/2010.00571v2","paper_title":"Understanding tables with intermediate pre-training","code":"https://github.com/google-research/tapas","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"TabSQLify (col+row)","metrics":{"Test":"79.5"},"uses_additional_data":false,"paper_date":"2024-04-15","paper":"/paper/tabsqlify-enhancing-reasoning-capabilities-of","paper_url":"https://arxiv.org/abs/2404.10150v1","paper_title":"TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition","code":"https://github.com/mahadi-nahid/tabsqlify","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":15}},{"rank_in_archive_order":13,"model":"NormTab (Targeted) + SQL","metrics":{"Test":"68.90"},"uses_additional_data":false,"paper_date":"2024-06-25","paper":"/paper/normtab-improving-symbolic-reasoning-in-llms","paper_url":"https://arxiv.org/abs/2406.17961v2","paper_title":"NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization","code":"https://github.com/mahadi-nahid/NormTab","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"Table-BERT-Horizontal-T+F-Template","metrics":{"Test":"65.12","Val":"66.1"},"uses_additional_data":false,"paper_date":"2019-09-05","paper":"/paper/tabfact-a-large-scale-dataset-for-table-based","paper_url":"https://arxiv.org/abs/1909.02164v5","paper_title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","code":"https://github.com/wenhuchen/Table-Fact-Checking","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":15,"model":"BERT classifier w/o Table","metrics":{"Test":"50.5","Val":"50.9"},"uses_additional_data":false,"paper_date":"2019-09-05","paper":"/paper/tabfact-a-large-scale-dataset-for-table-based","paper_url":"https://arxiv.org/abs/1909.02164v5","paper_title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","code":"https://github.com/wenhuchen/Table-Fact-Checking","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":2}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":8,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":19,"n_unverified":32,"n_samples":51,"n_pointer_only_licence":17,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":21,"n_unverified":33,"n_samples":54,"n_pointer_only_licence":19,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}