JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims

2024/01/16 by Fengzhu Zeng, Wei Gao, Zeng, Fengzhu +1 · 9 citations
Computer Science · #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2401.08026

openalex publication_date 2024/01/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Justification is an explanation that supports the veracity assigned to a claim in fact-checking. However, the task of justification generation is previously oversimplified as summarization of fact-check article authored by fact-checkers. Therefore, we propose a realistic approach to generate justification based on retrieved evidence. We present a new benchmark dataset called ExClaim for \underlineExplainable fact-checking of real-world \underlineClaims, and introduce JustiLM, a novel few-shot \underlineJustification generation based on retrieval-augmented \underlineLanguage \underlineModel by using fact-check articles as auxiliary resource during training only. Experiments show that JustiLM achieves promising performance in justification generation compared to strong baselines, and can also enhance veracity classification with a straightforward extension.

Cited by

• SourceMinds at CheckThat! 2026: NLI-Grounded Citation Auditing in a Multi-Agent Pipeline for Full Fact-Checking Article Generation
• LLM-based Few-Shot Early Rumor Detection with Imitation Agent
• EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detection
• REFLEX: Self-Refining Explainable Fact-Checking via Disentangling Truth into Style and Substance
• Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
• Commenotes: Synthesizing Organic Comments to Support Community-Based Fact-Checking
• Adversarial Attacks Against Automated Fact-Checking: A Survey
• Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification
• Generating Grounded Responses to Counter Misinformation via Learning Efficient Fine-Grained Critiques

Related

• Generating Fact Checking Explanations
• Benchmarking the Generation of Fact Checking Explanations
• Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs
• BOOST: Bootstrapping Strategy-Driven Reasoning Programs for Program-Guided Fact-Checking
• Mining the Explainability and Generalization: Fact Verification Based on Self-Instruction