Data to 7 Oct 2026

BERT for Evidence Retrieval and Claim Verification

arXiv 1910.02655 ↗First posted 7 Oct 2019cs.CLcited by 57

Not on the map. Why?

Abstract (arXiv)

Motivated by the promising performance of pre-trained language models, we investigate BERT in an evidence retrieval and claim verification pipeline for the FEVER fact extraction and verification challenge. To this end, we propose to use two BERT models, one for retrieving potential evidence sentences supporting or rejecting claims, and another for verifying claims based on the predicted evidence sets. To train the BERT retrieval system, we use pointwise and pairwise loss functions, and examine the effect of hard negative mining. A second BERT model is trained to classify the samples as supported, refuted, and not enough information. Our system achieves a new state of the art recall of 87.1 for retrieving top five sentences out of the FEVER documents consisting of 50K Wikipedia pages, and scores second in the official leaderboard with the FEVER score of 69.7.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 9; 2023: 9; 2024: 11; 2025: 14; 2026: 5.

57 papers.

Sort:

By area:

2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
2023Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Methodcited by 97
2022GERE: Generative Evidence Retrieval for Fact Verificationcited by 38
2023Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Modelscited by 31
2021Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verificationcited by 20
2022Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twittercited by 19
2021Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detectioncited by 17
2023From Chaos to Clarity: Claim Normalization to Empower Fact-Checkingcited by 17
2021Topic-Aware Evidence Reasoning and Stance-Aware Aggregation for Fact Verificationcited by 16
2021A Multi-Level Attention Model for Evidence-Based Fact Checkingcited by 13
2022Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Predictioncited by 12
2023BEVERS: A General, Simple, and Performant Framework for Automatic Fact Verificationcited by 11

38 more

2024CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checkingcited by 11
2023Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Mediacited by 8
2025BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checkingcited by 8
2022Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Tokencited by 7
2025Can LLMs Automate Fact-Checking Article Writing?cited by 7
2021Knowledge-Enhanced Evidence Retrieval for Counterargument Generationcited by 6
2021Hidden Biases in Unreliable News Detection Datasetscited by 5
2022Natural Language Inference with Self-Attention for Veracity Assessment of Pandemic Claimscited by 5
2022ProVe: A Pipeline for Automated Provenance Verification of Knowledge Graphs against Textual Sourcescited by 5
2024CFEVER: A Chinese Fact Extraction and VERification Datasetcited by 5
2024Heterogeneous Graph Reasoning for Fact Checking over Texts and Tablescited by 5
2025Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learningcited by 5
2022Artefact Retrieval: Overview of NLP Models with Knowledge Base Accesscited by 4
2022The COVMis-Stance dataset: Stance Detection on Twitter for COVID-19 Misinformationcited by 4
2023Investigating Zero- and Few-shot Generalization in Fact Verificationcited by 4
2023Overview of the CLAIMSCAN-2023: Uncovering Truth in Social Media through Claim Detection and Identification of Claim Spanscited by 4
2024ChronoFact: Timeline-based Temporal Fact Verificationcited by 4
2025A Graph-based Verification Framework for Fact-Checkingcited by 4
2024Navigating the Noisy Crowd: Finding Key Information for Claim Verificationcited by 3
2024Critical Questions Generation: Motivation and Challengescited by 3
2025STRIVE: Structured Reasoning for Self-Improvement in Claim Verificationcited by 3
2022Multiverse: Multilingual Evidence for Fake News Detectioncited by 2
2023Evidence-based Interpretable Open-domain Fact-checking with Large Language Modelscited by 2
2024Scope of Large Language Models for Mining Emerging Opinions in Online Health Discoursecited by 2
2025A Dynamic Knowledge Update-Driven Model with Large Language Models for Fake News Detectioncited by 2
2025Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Searchcited by 2
2025Towards Unification of Hallucination Detection and Fact Verification for Large Language Modelscited by 2
2026FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verificationcited by 2
2021An Analysis of a BERT Deep Learning Strategy on a Technology Assisted Review Taskcited by 1
2024M3: A Multi-Task Mixed-Objective Learning Framework for Open-Domain Multi-Hop Dense Sentence Retrievalcited by 1
2024Multi-Evidence based Fact Verification via A Confidential Graph Neural Networkcited by 1
2024Generative Debunking of Climate Misinformationcited by 1
2025CRAVE: A Conflicting Reasoning Approach for Explainable Claim Verification Using LLMscited by 1
2026Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectivenesscited by 1
2021Graph-based Retrieval for Claim Verification over Cross-Document Evidencecited by 0
2021Robust Information Retrieval for False Claims with Distracting Entities In Fact Extraction and Verificationcited by 0
2024Mining the Explainability and Generalization: Fact Verification Based on Self-Instructioncited by 0
2025Efficient Environmental Claim Detection with Hyperbolic Graph Neural Networkscited by 0

50 most cited of 57 All 57 (JSON)