EMNLP Findings2025
GraphCheck: Multipath Fact-Checking with Entity-Relationship Graphs
Hyewon Jeon, Jay-Yoon Lee
Abstract
Automated fact-checking aims to assess the truthfulness of textual claims based on relevant evidence. However, verifying complex claims that require multi-hop reasoning remains a significant challenge. We propose GraphCheck, a novel framework that transforms claims into entity-relationship graphs for structured and systematic fact-checking. By explicitly modeling both explicit and latent entities and exploring multiple reasoning paths, GraphCheck enhances verification robustness. While GraphCheck excels in complex scenarios, it may be unnecessarily elaborate for simpler claims. To address this, we introduce DP-GraphCheck, a variant that employs a lightweight strategy selector to choose between direct prompting and GraphCheck adaptively. This selective mechanism improves both accuracy and efficiency by applying the appropriate level of reasoning to each claim. Experiments on the HOVER and EX-FEVER datasets demonstrate that our approach outperforms existing methods in verification accuracy, while achieving strong computational efficiency despite its multipath exploration. Moreover, the strategy selection mechanism in DP-GraphCheck generalizes well to other factchecking pipelines, highlighting the broad applicability of our framework.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy cites Language Models are Few-Shot Learners
- Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification cites HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification
- Language Models are Few-Shot Learners cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks cites Reasoning Over Semantic-Level Graph for Fact Checking
Cited by top-tier papers1
Builds on10
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation SynergyZhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang et al.EMNLP Findings 2023 · 200 citations
- Reasoning Over Semantic-Level Graph for Fact CheckingWanjun Zhong, Jingjing Xu, Duyu Tang, Zenan Xu et al.ACL 2020 · 154 citations
- HoVer: A Dataset for Many-Hop Fact Extraction And Claim VerificationYichen Jiang, Shikha Bordia, Zheng Zhong, Charles Dognin et al.EMNLP Findings 2020 · 107 citations
Related papers
- MRR-FV: Unlocking Complex Fact Verification with Multi-Hop Retrieval and ReasoningLiwen Zheng, Chaozhuo Li, Litian Zhang, Haoran Jia et al.AAAI 2025 · 6 citations
- Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy OptimizationYunhan Bu, quan zhang, Zhang Huaping, Guotong Geng et al.ICML 2026
- Heterogeneous Graph Reasoning for Fact Checking over Texts and TablesHaisong Gong, Weizhi Xu, Shu Wu, Qiang Liu et al.AAAI 2024 · 19 citations
- BiDeV: Bilateral Defusing Verification for Complex Claim Fact-CheckingYuxuan Liu, Hongda Sun, Wenya Guo, Xinyan Xiao et al.AAAI 2025 · 11 citations
- A Multi-Level Attention Model for Evidence-Based Fact CheckingCanasai Kruengkrai, Junichi Yamagishi, Xin WangACL Findings 2021 · 17 citations
