JustiLM：面向真实世界声明可解释事实核查的小样本理由生成
JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims
AI总结：
本文针对事实核查中理由生成被简化为摘要的问题，提出基于检索证据的JustiLM小样本方法，并发布ExClaim基准数据集，实验证明其能提升理由生成与真实性分类性能。
摘要：
理由是一种解释，用于支持事实核查中赋予某一断言的真实性判定。然而，理由生成任务此前被过度简化为对事实核查员撰写的事实核查文章的摘要。因此，我们提出一种基于检索证据生成理由的现实方法。我们发布了一个新的基准数据集ExClaim，用于真实世界声明的可解释事实核查，并引入JustiLM，这是一种新颖的小样本理由生成方法，基于检索增强语言模型，仅在训练阶段使用事实核查文章作为辅助资源。实验表明，与强基线相比，JustiLM在理由生成方面取得了有前景的性能，并且通过直接扩展还能提升真实性分类效果。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
