SOTAVerified

Fact Verification

Fact verification, also called "fact checking", is a process of verifying facts in natural text against a database of facts.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 216 papers

TitleStatusHype
Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMsCode2
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table UnderstandingCode2
Learning to Filter Context for Retrieval-Augmented GenerationCode2
Precise Zero-Shot Dense Retrieval without Relevance LabelsCode2
Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact VerifiersCode1
Table-R1: Inference-Time Scaling for Table ReasoningCode1
HIPPO: Enhancing the Table Understanding Capability of Large Language Models through Hybrid-Modal Preference OptimizationCode1
Assessing the Limitations of Large Language Models in Clinical Fact DecompositionCode1
Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OasisCode1
CHECKWHY: Causal Fact Verification via Argument StructureCode1
Show:102550
← PrevPage 2 of 22Next →
All datasetsKILT: FEVERFEVERDanFEVER

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Re2GKILT-AC78.53—Unverified
2intersectKILT-AC71.28—Unverified
3WikipediaKILT-AC65.68—Unverified
4KGIKILT-AC64.41—Unverified
5Multitask DPR + BARTKILT-AC63.94—Unverified
6BERT + DPRKILT-AC58.58—Unverified
7RAGKILT-AC53.45—Unverified
8BART + DPRKILT-AC47.68—Unverified
9NSMNKILT-AC41.88—Unverified
10T5-baseKILT-AC0—Unverified
#ModelMetricClaimedVerifiedStatus
1ProoFVer-SBAccuracy79.47—Unverified
2DREAMAccuracy76.85—Unverified
3RoBERTa-Base Joint MSPP FlexibleAccuracy75.36—Unverified
4RoBERTa-Base Joint MSPPAccuracy74.39—Unverified
5KGATAccuracy74.1—Unverified
6RAGAccuracy72.5—Unverified
7GEARAccuracy71.6—Unverified
#ModelMetricClaimedVerifiedStatus
1DanFEVER XLM-RoBERTa LargeF10.9—Unverified