# Fact

Source: [Fact](<https://www.sota2.com/research/task/fact>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.



## Benchmarks

Page 1 of 23. This is an index page, not the full collection.

- [Next index page](<https://www.sota2.com/research/task/fact.md?page=2>): Follow this link to discover more pages.

- [Table Fact Verification on TabFact (test)](<https://www.sota2.com/research/sota/table-fact-verification-on-tabfact-test.md>): Table Fact Verification; TabFact (test).

- [Accuracy Evaluation on TruthfulQA](<https://www.sota2.com/research/sota/accuracy-evaluation-on-truthfulqa.md>): Factuality; TruthfulQA.

- [JPEG Artifact Reduction on LIVE1](<https://www.sota2.com/research/sota/jpeg-artifact-reduction-on-live1.md>): JPEG artifact reduction; LIVE1.

- [Fact Checking on TableBench (test)](<https://www.sota2.com/research/sota/fact-checking-on-tablebench-test.md>): Fact Checking; TableBench (test).

- [Table Fact Verification on TabFact](<https://www.sota2.com/research/sota/table-fact-verification-on-tabfact.md>): Table Fact Verification; TabFact.

- [Table-based Fact Verification on TabFact](<https://www.sota2.com/research/sota/table-based-fact-verification-on-tabfact.md>): Table-based Fact Verification; TabFact.

- [JPEG Image Artifacts Removal on LIVE1](<https://www.sota2.com/research/sota/jpeg-image-artifacts-removal-on-live1.md>): JPEG image artifacts removal; LIVE1.

- [Factual outcome prediction on MIMIC-III extract](<https://www.sota2.com/research/sota/factual-outcome-prediction-on-mimic-iii-extract.md>): Factual outcome prediction; MIMIC-III extract.

- [Factuality Evaluation on TruthfulQA](<https://www.sota2.com/research/sota/factuality-evaluation-on-truthfulqa.md>): Factuality Evaluation; TruthfulQA.

- [Fact Checking on RealHitBench](<https://www.sota2.com/research/sota/fact-checking-on-realhitbench.md>): Fact Checking; RealHitBench.

- [JPEG Compression Artifact Reduction on Classic5 (PSNR, SSIM)](<https://www.sota2.com/research/sota/jpeg-compression-artifact-reduction-on-classic5-psnr-ssim.md>): JPEG compression artifact reduction; Classic5.

- [Fact Verification on TabFact](<https://www.sota2.com/research/sota/fact-verification-on-tabfact.md>): Fact Verification; TabFact.

- [Counterfactual Generation on SIB200](<https://www.sota2.com/research/sota/counterfactual-generation-on-sib200.md>): Counterfactual Generation; SIB200.

- [Counterfactual Tumor Growth Prediction on PK-PD tumor growth simulator (test)](<https://www.sota2.com/research/sota/counterfactual-tumor-growth-prediction-on-pk-pd-tumor-growth-simulator-test.md>): Counterfactual Tumor Growth Prediction; PK-PD tumor growth simulator (test).

- [Counterfactual Outcome Estimation on Tumor Growth tau=2 synthetic (test)](<https://www.sota2.com/research/sota/counterfactual-outcome-estimation-on-tumor-growth-tau-2-synthetic-test.md>): Counterfactual Outcome Estimation; Tumor Growth tau=2 synthetic (test).

- [Fact Verification on FEVER](<https://www.sota2.com/research/sota/fact-verification-on-fever.md>): Fact Verification; FEVER.

- [Artifact Detection on OpenMMSec](<https://www.sota2.com/research/sota/artifact-detection-on-openmmsec.md>): Artifact Detection; OpenMMSec.

- [Counterfactual Generation on TAXI1500](<https://www.sota2.com/research/sota/counterfactual-generation-on-taxi1500.md>): Counterfactual Generation; TAXI1500.

- [Fact-based Visual Question Answering on FVQA](<https://www.sota2.com/research/sota/fact-based-visual-question-answering-on-fvqa.md>): Fact-based Visual Question Answering; FVQA.

- [Factuality Correction on VELI5](<https://www.sota2.com/research/sota/factuality-correction-on-veli5.md>): Factuality Correction; VELI5.

- [Matrix Factorization Utility on Balls-in-Bins accountant n=2048, k=8](<https://www.sota2.com/research/sota/matrix-factorization-utility-on-balls-in-bins-accountant-n-2048-k-8.md>): Matrix Factorization Utility; Balls-in-Bins accountant n=2048, k=8.

- [Factual code question answering on CodeSimpleQA English 1.0](<https://www.sota2.com/research/sota/factual-code-question-answering-on-codesimpleqa-english-1-0.md>): Factual code question answering; CodeSimpleQA English 1.0.

- [Factuality Detection on Short-form QA (Average of NQ, PopQA, TriviaQA, SimpleQA) (test)](<https://www.sota2.com/research/sota/factuality-detection-on-short-form-qa-average-of-nq-popqa-triviaqa-simpleqa-test.md>): Factuality Detection; Short-form QA (Average of NQ, PopQA, TriviaQA, SimpleQA) (test).

- [Grayscale JPEG compression artifact removal on Classic5](<https://www.sota2.com/research/sota/grayscale-jpeg-compression-artifact-removal-on-classic5.md>): Grayscale JPEG compression artifact removal; Classic5.

- [Counterfactual outcome prediction on MIMIC III semi-synthetic (800/200/200)](<https://www.sota2.com/research/sota/counterfactual-outcome-prediction-on-mimic-iii-semi-synthetic-800-200-200.md>): Counterfactual outcome prediction; MIMIC III semi-synthetic (800/200/200).

- [Table Fact Verification on TABFACT small (test)](<https://www.sota2.com/research/sota/table-fact-verification-on-tabfact-small-test.md>): Table Fact Verification; TABFACT small (test).

- [Fact Verification on FEVER (dev)](<https://www.sota2.com/research/sota/fact-verification-on-fever-dev.md>): Fact Verification; FEVER (dev).

- [Factual Knowledge Evaluation on PopQA](<https://www.sota2.com/research/sota/factual-knowledge-evaluation-on-popqa.md>): Factual Knowledge Evaluation; PopQA.

- [Artifact Suppression on Real-world Automotive Sequences Sun and Zurich City](<https://www.sota2.com/research/sota/artifact-suppression-on-real-world-automotive-sequences-sun-and-zurich-city.md>): Artifact Suppression; Real-world Automotive Sequences Sun and Zurich City.

- [Counterfactual Reasoning on Counterfactual Eval (dev)](<https://www.sota2.com/research/sota/counterfactual-reasoning-on-counterfactual-eval-dev.md>): Counterfactual Reasoning; Counterfactual Eval (dev).

- [Factual Consistency Evaluation on SummaC](<https://www.sota2.com/research/sota/factual-consistency-evaluation-on-summac.md>): Factual Consistency Evaluation; SummaC.

- [Long-form QA Factuality Detection on Long-form QA Benchmark](<https://www.sota2.com/research/sota/long-form-qa-factuality-detection-on-long-form-qa-benchmark.md>): Long-form QA Factuality Detection; Long-form QA benchmark factuality target.

- [Fact Verification on FEVER (val)](<https://www.sota2.com/research/sota/fact-verification-on-fever-val.md>): Fact Verification; FEVER (val).

- [Factual question answering on TriviaQA](<https://www.sota2.com/research/sota/factual-question-answering-on-triviaqa.md>): Factual question answering; TriviaQA.

- [Fact Verification on PubMed (test)](<https://www.sota2.com/research/sota/fact-verification-on-pubmed-test.md>): Fact verification; PubMed (test).

- [Fact Accuracy on Synthetic Phonebook Facts Power law Exponent beta = 0.5](<https://www.sota2.com/research/sota/fact-accuracy-on-synthetic-phonebook-facts-power-law-exponent-beta-0-5.md>): Fact Accuracy; Synthetic Phonebook Facts Power law Exponent beta = 0.5.

- [Fact-based Question Answering on FVQA (test)](<https://www.sota2.com/research/sota/fact-based-question-answering-on-fvqa-test.md>): Fact-based Question Answering; FVQA (test).

- [Table Fact Verification on InfoTabs](<https://www.sota2.com/research/sota/table-fact-verification-on-infotabs.md>): Table Fact Verification; InfoTabs.

- [Factuality Correction on BIO (test)](<https://www.sota2.com/research/sota/factuality-correction-on-bio-test.md>): Factuality Correction; BIO (test).

- [Factual Knowledge on BoolQ](<https://www.sota2.com/research/sota/factual-knowledge-on-boolq.md>): Factual Knowledge; Bool Q.

- [Tool-use Factuality Evaluation on BFCL Task](<https://www.sota2.com/research/sota/tool-use-factuality-evaluation-on-bfcl-task.md>): Tool-use Factuality Evaluation; BFCL Task.

- [Tool-use Factuality Evaluation on InvivoQuery](<https://www.sota2.com/research/sota/tool-use-factuality-evaluation-on-invivoquery.md>): Tool-use Factuality Evaluation; InvivoQuery.

- [Tool-use Factuality Evaluation on Entity Task](<https://www.sota2.com/research/sota/tool-use-factuality-evaluation-on-entity-task.md>): Tool-use Factuality Evaluation; Entity Task.

- [Counterfactual Prediction on Synthetic Dataset (RMSEy)](<https://www.sota2.com/research/sota/counterfactual-prediction-on-synthetic-dataset-rmsey.md>): Counterfactual Prediction; Synthetic Dataset.

- [Counterfactual Prediction on Synthetic Dataset (test)](<https://www.sota2.com/research/sota/counterfactual-prediction-on-synthetic-dataset-test.md>): Counterfactual Prediction; Synthetic Dataset (test).

- [Counterfactual Prediction (ATE Error) on Synthetic Dataset](<https://www.sota2.com/research/sota/counterfactual-prediction-ate-error-on-synthetic-dataset.md>): Counterfactual Prediction; Synthetic Dataset.

- [Fact Accuracy on Synthetic Phonebook Facts Power law Exponent beta = 1.0](<https://www.sota2.com/research/sota/fact-accuracy-on-synthetic-phonebook-facts-power-law-exponent-beta-1-0.md>): Fact Accuracy; Synthetic Phonebook Facts Power law Exponent beta = 1.0.

- [Fact Accuracy on Synthetic Phonebook Facts Power law Exponent beta = 0](<https://www.sota2.com/research/sota/fact-accuracy-on-synthetic-phonebook-facts-power-law-exponent-beta-0.md>): Fact Accuracy; Synthetic Phonebook Facts Power law Exponent beta = 0.

- [Counterfactual Reasoning on CVQA](<https://www.sota2.com/research/sota/counterfactual-reasoning-on-cvqa.md>): Counterfactual Reasoning; CVQA.

- [Factuality Correction on ASKHIST](<https://www.sota2.com/research/sota/factuality-correction-on-askhist.md>): Factuality Correction; ASKHIST.

- [Factuality-based Question Answering on FreshQA 2025/11/24](<https://www.sota2.com/research/sota/factuality-based-question-answering-on-freshqa-2025-11-24.md>): Factuality-based Question Answering; FreshQA 2025/11/24.

- [Factual Consistency Evaluation on QAGS-XSum (Spearman correlation)](<https://www.sota2.com/research/sota/factual-consistency-evaluation-on-qags-xsum-spearman-correlation.md>): Factual Consistency Evaluation; QAGS-XSum.

- [Table Fact Verification on TABFACT complex (test)](<https://www.sota2.com/research/sota/table-fact-verification-on-tabfact-complex-test.md>): Table Fact Verification; TABFACT complex (test).

- [Table Fact Verification on TABFACT simple (test)](<https://www.sota2.com/research/sota/table-fact-verification-on-tabfact-simple-test.md>): Table Fact Verification; TABFACT simple (test).

- [Factual Consistency Evaluation on QAGS CNNDM](<https://www.sota2.com/research/sota/factual-consistency-evaluation-on-qags-cnndm.md>): Factual Consistency Evaluation; QAGS CNNDM.

- [Counterfactual Generation on SNLI Hypothesis](<https://www.sota2.com/research/sota/counterfactual-generation-on-snli-hypothesis.md>): Counterfactual Generation; SNLI Hypothesis.

- [Counterfactual Generation on SNLI Premise](<https://www.sota2.com/research/sota/counterfactual-generation-on-snli-premise.md>): Counterfactual Generation; SNLI Premise.

- [Counterfactual Generation on AG News](<https://www.sota2.com/research/sota/counterfactual-generation-on-ag-news.md>): Counterfactual Generation; AG News.

- [Counterfactual Generation on IMDb](<https://www.sota2.com/research/sota/counterfactual-generation-on-imdb.md>): Counterfactual Generation; IMDb.

- [Factual Consistency Evaluation on TRUE benchmark](<https://www.sota2.com/research/sota/factual-consistency-evaluation-on-true-benchmark.md>): Factual Consistency Evaluation; TRUE benchmark.

- [Factual QA on NQ-Open](<https://www.sota2.com/research/sota/factual-qa-on-nq-open.md>): Factual QA; NQ-Open.

- [Global Counterfactual Explanations on HELOC](<https://www.sota2.com/research/sota/global-counterfactual-explanations-on-heloc.md>): Global Counterfactual Explanations; HELOC.

- [Global Counterfactual Explanations on German Credit](<https://www.sota2.com/research/sota/global-counterfactual-explanations-on-german-credit.md>): Global Counterfactual Explanations; German Credit.

- [Global Counterfactual Explanations on Default Credit](<https://www.sota2.com/research/sota/global-counterfactual-explanations-on-default-credit.md>): Global Counterfactual Explanations; Default Credit.

- [Global Counterfactual Explanations on COMPAS](<https://www.sota2.com/research/sota/global-counterfactual-explanations-on-compas.md>): Global Counterfactual Explanations; COMPAS.

- [Metal Artifact Restoration on SynDeepLesion Tiny size (test)](<https://www.sota2.com/research/sota/metal-artifact-restoration-on-syndeeplesion-tiny-size-test.md>): Metal Artifact Restoration; SynDeepLesion Tiny size (test).

- [Metal Artifact Restoration on SynDeepLesion Small size (test)](<https://www.sota2.com/research/sota/metal-artifact-restoration-on-syndeeplesion-small-size-test.md>): Metal Artifact Restoration; SynDeepLesion Small size (test).

- [Counterfactual Inference on CFInfer](<https://www.sota2.com/research/sota/counterfactual-inference-on-cfinfer.md>): Counterfactual Inference; CFInfer.

- [Legal Domain Fabrication and Factuality Analysis on JURIDICO-FCR 75 tasks](<https://www.sota2.com/research/sota/legal-domain-fabrication-and-factuality-analysis-on-juridico-fcr-75-tasks.md>): Legal Domain Fabrication and Factuality Analysis; JURIDICO-FCR 75 tasks.

- [Factual Consistency Evaluation on SummEval](<https://www.sota2.com/research/sota/factual-consistency-evaluation-on-summeval.md>): Factual Consistency Evaluation; SummEval.

- [Counterfactual Outcome Prediction on MIMIC-III semi-synthetic (N=3000) (test)](<https://www.sota2.com/research/sota/counterfactual-outcome-prediction-on-mimic-iii-semi-synthetic-n-3000-test.md>): Counterfactual Outcome Prediction; MIMIC-III semi-synthetic (N=3000) (test).

- [Counterfactual Outcome Prediction on MIMIC-III semi-synthetic (N=2000) (test)](<https://www.sota2.com/research/sota/counterfactual-outcome-prediction-on-mimic-iii-semi-synthetic-n-2000-test.md>): Counterfactual Outcome Prediction; MIMIC-III semi-synthetic (N=2000) (test).

- [Counterfactual Outcome Prediction on MIMIC-III semi-synthetic (N=1000) (test)](<https://www.sota2.com/research/sota/counterfactual-outcome-prediction-on-mimic-iii-semi-synthetic-n-1000-test.md>): Counterfactual Outcome Prediction; MIMIC-III semi-synthetic (N=1000) (test).

- [Factor Analysis on LOOPR (in-sample)](<https://www.sota2.com/research/sota/factor-analysis-on-loopr-in-sample.md>): Factor Analysis; LOOPR (in-sample).

- [Factual Consistency Evaluation on QAGS-XSum (test)](<https://www.sota2.com/research/sota/factual-consistency-evaluation-on-qags-xsum-test.md>): Factual Consistency Evaluation; QAGS-XSum (test).

- [Constraint Satisfaction Reasoning on Countdown](<https://www.sota2.com/research/sota/constraint-satisfaction-reasoning-on-countdown.md>): Constraint Satisfaction Reasoning; Countdown.

- [Fact Checking on LIAR (Acc@1, Avg. Perf.)](<https://www.sota2.com/research/sota/fact-checking-on-liar-acc-at-1-avg-perf.md>): Fact Checking; LIAR.

- [Counterfactual Input Evaluation on CrowS-Pairs](<https://www.sota2.com/research/sota/counterfactual-input-evaluation-on-crows-pairs.md>): Counterfactual Input Evaluation; CrowS-Pairs.

- [Factuality Question Answering on SampleQA (Accuracy %)](<https://www.sota2.com/research/sota/factuality-question-answering-on-sampleqa-accuracy-percent.md>): Factuality Question Answering; SampleQA.

- [Long-form Factuality on FActScore](<https://www.sota2.com/research/sota/long-form-factuality-on-factscore.md>): Long-form Factuality; FActScore.
