Enhancing Multi-Hop Fact Verification with Structured Knowledge-Augmented Large Language Models

2025-03-11

AI Summary

Multi-hop fact verification faces challenges in cross-evidence reasoning and reliance on complex, fine-grained entity relation modeling. Method: This paper proposes LLM-SKAN—a Structured Knowledge-Augmented Network—that uniquely employs large language models (LLMs) as fine-grained relation extractors—not end-to-end predictors—to construct entity-relation graphs. It introduces a knowledge-enhanced graph fusion module and a multi-hop evidence interaction representation module to enable logically interpretable, graph-based reasoning. Contribution/Results: By transcending single-hop semantic matching, LLM-SKAN achieves significant improvements over state-of-the-art methods on four benchmark datasets—FEVEROUS, MultiFC, SciFact, and HoVer—demonstrating that structured relation modeling enhances both accuracy and generalizability in multi-hop fact verification.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

The rapid development of social platforms exacerbates the dissemination of misinformation, which stimulates the research in fact verification. Recent studies tend to leverage semantic features to solve this problem as a single-hop task. However, the process of verifying a claim requires several pieces of evidence with complicated inner logic and relations to verify the given claim in real-world situations. Recent studies attempt to improve both understanding and reasoning abilities to enhance the performance, but they overlook the crucial relations between entities that benefit models to understand better and facilitate the prediction. To emphasize the significance of relations, we resort to Large Language Models (LLMs) considering their excellent understanding ability. Instead of other methods using LLMs as the predictor, we take them as relation extractors, for they do better in understanding rather than reasoning according to the experimental results. Thus, to solve the challenges above, we propose a novel Structured Knowledge-Augmented LLM-based Network (LLM-SKAN) for multi-hop fact verification. Specifically, we utilize an LLM-driven Knowledge Extractor to capture fine-grained information, including entities and their complicated relations. Besides, we leverage a Knowledge-Augmented Relation Graph Fusion module to interact with each node and learn better claim-evidence representations comprehensively. The experimental results on four common-used datasets demonstrate the effectiveness and superiority of our model.

Problem

• Addresses multi-hop fact verification challenges
• Enhances understanding of entity relations in claims
• Proposes a structured knowledge-augmented LLM-based network

Innovation

• Uses LLMs as relation extractors
• Develops Structured Knowledge-Augmented LLM-based Network
• Integrates Knowledge-Augmented Relation Graph Fusion