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

Abstract

Justification is an explanation that supports the veracity assigned to a claim in fact-checking. However, the task of justification generation has been previously oversimplified as summarization of a fact-check article authored by factcheckers. Therefore, we propose a realistic approach to generate justification based on retrieved evidence. We present a new benchmark dataset called ExClaim (for Explainable factchecking of real-world Claims), and introduce JustiLM, a novel few-shot Justification generation based on retrieval-augmented Language Model by using fact-check articles as an 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.1.