JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims
This work addresses the need for explainable fact-checking of real-world claims, offering a novel method that improves over oversimplified summarization approaches.
The paper tackles the problem of generating justifications for fact-checking claims by proposing a realistic approach based on retrieved evidence, introducing a new benchmark dataset ExClaim and a few-shot model JustiLM, which achieves promising performance in justification generation and enhances veracity classification.
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 \underline{Ex}plainable fact-checking of real-world \underline{Claim}s, and introduce JustiLM, a novel few-shot \underline{Justi}fication generation based on retrieval-augmented \underline{L}anguage \underline{M}odel 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.