mlsanityData to 14 Oct 2026

Fine-grained Fact Verification with Kernel Graph Attention Network

arXiv 1910.09796 ↗First posted 22 Oct 2019cs.CLcited by 105

Not on the map. Why?

Abstract (arXiv)

Fact Verification requires fine-grained natural language inference capability that finds subtle clues to identify the syntactical and semantically correct but not well-supported claims. This paper presents Kernel Graph Attention Network (KGAT), which conducts more fine-grained fact verification with kernel-based attentions. Given a claim and a set of potential evidence sentences that form an evidence graph, KGAT introduces node kernels, which better measure the importance of the evidence node, and edge kernels, which conduct fine-grained evidence propagation in the graph, into Graph Attention Networks for more accurate fact verification. KGAT achieves a 70.38% FEVER score and significantly outperforms existing fact verification models on FEVER, a large-scale benchmark for fact verification. Our analyses illustrate that, compared to dot-product attentions, the kernel-based attention concentrates more on relevant evidence sentences and meaningful clues in the evidence graph, which is the main source of KGAT's effectiveness.

Key facts. Cited by 105 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 21; 2023: 25; 2024: 20; 2025: 7; 2026: 7.

105 papers.

Sort:

By area:

  1. 2021A Survey on Automated Fact-Checkingcited by 378
  2. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 274
  3. 2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 155
  4. 2023Fact-Checking Complex Claims with Program-Guided Reasoningcited by 146
  5. 2021GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graphcited by 143
  6. 2023Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learningcited by 133
  7. 2021A Survey on Stance Detection for Mis- and Disinformation Identificationcited by 75
  8. 2024Can GNN be Good Adapter for LLMs?cited by 71
  9. 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
  10. 2024GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Taskscited by 63
  11. 2021DialFact: A Benchmark for Fact-Checking in Dialoguecited by 62
  12. 2023Scientific Fact-Checking: A Survey of Resources and Approachescited by 54
38 more
  1. 2021ProoFVer: Natural Logic Theorem Proving for Fact Verificationcited by 53
  2. 2021Fool Me Twice: Entailment from Wikipedia Gamificationcited by 50
  3. 2022Synthetic Disinformation Attacks on Automated Fact Verification Systemscited by 44
  4. 2021Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classificationcited by 43
  5. 2021Zero-shot Fact Verification by Claim Generationcited by 42
  6. 2021Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answeringcited by 41
  7. 2022GERE: Generative Evidence Retrieval for Fact Verificationcited by 38
  8. 2022CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checkingcited by 37
  9. 2023Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Modelscited by 37
  10. 2023EX-FEVER: A Dataset for Multi-hop Explainable Fact Verificationcited by 36
  11. 2022Zoom Out and Observe: News Environment Perception for Fake News Detectioncited by 34
  12. 2021Towards Fine-Grained Reasoning for Fake News Detectioncited by 32
  13. 2022Evidence-aware Fake News Detection with Graph Neural Networkscited by 30
  14. 2022A Survey of Knowledge-Intensive NLP with Pre-Trained Language Modelscited by 30
  15. 2023QACHECK: A Demonstration System for Question-Guided Multi-Hop Fact-Checkingcited by 26
  16. 2023FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledgecited by 25
  17. 2022Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networkscited by 24
  18. 2021Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verificationcited by 20
  19. 2021The Role of Context in Detecting Previously Fact-Checked Claimscited by 17
  20. 2021Overview and Insights from the SciVer Shared Task on Scientific Claim Verificationcited by 17
  21. 2023Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidencecited by 17
  22. 2021Topic-Aware Evidence Reasoning and Stance-Aware Aggregation for Fact Verificationcited by 16
  23. 2021Explainable Fact-checking through Question Answeringcited by 16
  24. 2022Contrastive Domain Adaptation for Early Misinformation Detection: A Case Study on COVID-19cited by 15
  25. 2024Do We Need Language-Specific Fact-Checking Models? The Case of Chinesecited by 15
  26. 2021A Multi-Level Attention Model for Evidence-Based Fact Checkingcited by 13
  27. 2021Joint Models for Answer Verification in Question Answering Systemscited by 13
  28. 2022Claim-Dissector: An Interpretable Fact-Checking System with Joint Re-ranking and Veracity Predictioncited by 12
  29. 2022Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systemscited by 12
  30. 2021Exploring Decomposition for Table-based Fact Verificationcited by 11
  31. 2022Calibration of Machine Reading Systems at Scalecited by 11
  32. 2022Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verificationcited by 11
  33. 2023BEVERS: A General, Simple, and Performant Framework for Automatic Fact Verificationcited by 11
  34. 2024CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checkingcited by 11
  35. 2021Unified Dual-view Cognitive Model for Interpretable Claim Verificationcited by 10
  36. 2024FACTOID: FACtual enTailment fOr hallucInation Detectioncited by 10
  37. 2024FactLens: Benchmarking Fine-Grained Fact Verificationcited by 10
  38. 2023MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learningcited by 8

50 most cited of 105 All 105 (JSON)