mlsanityData to 14 Oct 2026

GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification

arXiv 1908.01843 ↗First posted 22 Jul 2019cs.CL cs.AI cs.LGcited by 100

Not on the map. Why?

Abstract (arXiv)

Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to verify given claims. Many claims require to simultaneously integrate and reason over several pieces of evidence for verification. However, previous work employs simple models to extract information from evidence without letting evidence communicate with each other, e.g., merely concatenate the evidence for processing. Therefore, these methods are unable to grasp sufficient relational and logical information among the evidence. To alleviate this issue, we propose a graph-based evidence aggregating and reasoning (GEAR) framework which enables information to transfer on a fully-connected evidence graph and then utilizes different aggregators to collect multi-evidence information. We further employ BERT, an effective pre-trained language representation model, to improve the performance. Experimental results on a large-scale benchmark dataset FEVER have demonstrated that GEAR could leverage multi-evidence information for FV and thus achieves the promising result with a test FEVER score of 67.10%. Our code is available at https://github.com/thunlp/GEAR.

Key facts. Cited by 100 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 16; 2023: 15; 2024: 17; 2025: 16; 2026: 11.

100 papers.

Sort:

By area:

  1. 2021A Survey on Automated Fact-Checkingcited by 378
  2. 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
  3. 2021GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graphcited by 143
  4. 2023Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learningcited by 133
  5. 2023WiCE: Real-World Entailment for Claims in Wikipediacited by 120
  6. 2021A Survey on Stance Detection for Mis- and Disinformation Identificationcited by 75
  7. 2021Towards Few-Shot Fact-Checking via Perplexitycited by 63
  8. 2021DialFact: A Benchmark for Fact-Checking in Dialoguecited by 62
  9. 2023FactKG: Fact Verification via Reasoning on Knowledge Graphscited by 57
  10. 2021Fool Me Twice: Entailment from Wikipedia Gamificationcited by 50
  11. 2022Synthetic Disinformation Attacks on Automated Fact Verification Systemscited by 44
  12. 2021Zero-shot Fact Verification by Claim Generationcited by 42
38 more
  1. 2022GERE: Generative Evidence Retrieval for Fact Verificationcited by 38
  2. 2022CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checkingcited by 37
  3. 2023Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Modelscited by 37
  4. 2023EX-FEVER: A Dataset for Multi-hop Explainable Fact Verificationcited by 36
  5. 2023KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Modelscited by 32
  6. 2022Evidence-aware Fake News Detection with Graph Neural Networkscited by 30
  7. 2022A Survey of Knowledge-Intensive NLP with Pre-Trained Language Modelscited by 30
  8. 2024Knowledge Graph-Enhanced Large Language Models via Path Selectioncited by 28
  9. 2022Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networkscited by 24
  10. 2023Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformationcited by 21
  11. 2021Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verificationcited by 20
  12. 2021Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detectioncited by 17
  13. 2021The Role of Context in Detecting Previously Fact-Checked Claimscited by 17
  14. 2021Topic-Aware Evidence Reasoning and Stance-Aware Aggregation for Fact Verificationcited by 16
  15. 2022Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detectioncited by 14
  16. 2021A Multi-Level Attention Model for Evidence-Based Fact Checkingcited by 13
  17. 2022Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Predictioncited by 12
  18. 2022Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systemscited by 12
  19. 2021Unified Dual-view Cognitive Model for Interpretable Claim Verificationcited by 10
  20. 2021Table-based Fact Verification with Salience-aware Learningcited by 9
  21. 2022Paragraph-based Transformer Pre-training for Multi-Sentence Inferencecited by 7
  22. 2022Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networkscited by 7
  23. 2023Out-of-distribution Evidence-aware Fake News Detection via Dual Adversarial Debiasingcited by 7
  24. 2024GraphNarrator: Generating Textual Explanations for Graph Neural Networkscited by 7
  25. 2025Can LLMs Automate Fact-Checking Article Writing?cited by 7
  26. 2021Diagnostics-Guided Explanation Generationcited by 6
  27. 2021Graph Reasoning with Context-Aware Linearization for Interpretable Fact Extraction and Verificationcited by 6
  28. 2023Plug-and-Play Knowledge Injection for Pre-trained Language Modelscited by 6
  29. 2024SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generationcited by 6
  30. 2025ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioningcited by 6
  31. 2021Constraint 2021: Machine Learning Models for COVID-19 Fake News Detection Shared Taskcited by 5
  32. 2022Natural Language Inference with Self-Attention for Veracity Assessment of Pandemic Claimscited by 5
  33. 2022ProVe: A Pipeline for Automated Provenance Verification of Knowledge Graphs against Textual Sourcescited by 5
  34. 2023Unsupervised Pretraining for Fact Verification by Language Model Distillationcited by 5
  35. 2024Heterogeneous Graph Reasoning for Fact Checking over Texts and Tablescited by 5
  36. 2025CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checkingcited by 5
  37. 2021Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verificationcited by 4
  38. 2023Give Me More Details: Improving Fact-Checking with Latent Retrievalcited by 4

50 most cited of 100 All 100 (JSON)