SOTAVerified

Fact Verification

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

Papers

Showing 76100 of 216 papers

TitleStatusHype
XFEVER: Exploring Fact Verification across LanguagesCode0
Language Models Hallucinate, but May Excel at Fact VerificationCode0
EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact VerificationCode0
QA-NatVer: Question Answering for Natural Logic-based Fact VerificationCode0
From Relevance to Utility: Evidence Retrieval with Feedback for Fact VerificationCode0
KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language ModelsCode1
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionCode4
EX-FEVER: A Dataset for Multi-hop Explainable Fact VerificationCode1
From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and ContextCode0
Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting MethodCode1
Unsupervised Pretraining for Fact Verification by Language Model DistillationCode0
Investigating Zero- and Few-shot Generalization in Fact VerificationCode0
Structural Self-Supervised Objectives for TransformersCode0
Findings of Factify 2: Multimodal Fake News Detection0
Heuristic Heterogeneous Graph Reasoning Networks for Fact VerificationCode0
Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language ModelsCode0
AlignScore: Evaluating Factual Consistency with a Unified Alignment FunctionCode4
Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation SynergyCode0
Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering0
FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering0
Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification0
Growing and Serving Large Open-domain Knowledge Graphs0
FactKG: Fact Verification via Reasoning on Knowledge GraphsCode1
Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact VerificationCode1
FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering0
Show:102550
← PrevPage 4 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Re2GKILT-AC78.53Unverified
2intersectKILT-AC71.28Unverified
3WikipediaKILT-AC65.68Unverified
4KGIKILT-AC64.41Unverified
5Multitask DPR + BARTKILT-AC63.94Unverified
6BERT + DPRKILT-AC58.58Unverified
7RAGKILT-AC53.45Unverified
8BART + DPRKILT-AC47.68Unverified
9NSMNKILT-AC41.88Unverified
10T5-baseKILT-AC0Unverified
#ModelMetricClaimedVerifiedStatus
1ProoFVer-SBAccuracy79.47Unverified
2DREAMAccuracy76.85Unverified
3RoBERTa-Base Joint MSPP FlexibleAccuracy75.36Unverified
4RoBERTa-Base Joint MSPPAccuracy74.39Unverified
5KGATAccuracy74.1Unverified
6RAGAccuracy72.5Unverified
7GEARAccuracy71.6Unverified
#ModelMetricClaimedVerifiedStatus
1DanFEVER XLM-RoBERTa LargeF10.9Unverified