采用分层逐步提示方法实现基于LLM的新闻声明事实验证
Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method
AI总结：
本文研究LLM在新闻声明事实验证中的应用，提出分层逐步HiSS提示方法，通过拆分声明并多步问答验证，在两个数据集上超过全监督SOTA与少样本ICL基线。
摘要：
尽管大型预训练语言模型（LLM）已在各类NLP任务中展现出令人瞩目的能力，但它们在虚假信息领域仍未得到充分探索。本文考察了利用上下文学习（ICL）进行新闻声明验证的LLM，发现仅需4个示例演示，若干提示方法的性能便可与此前的监督模型相媲美。为进一步提升性能，我们提出一种分层逐步（HiSS）提示方法，引导LLM将一项声明拆分为若干子声明，随后通过多个问答步骤逐步验证每个子声明。在两个公开虚假信息数据集上的实验结果表明，HiSS提示优于最先进的全监督方法以及强大的少样本ICL基线。
英文摘要：
While large pre-trained language models (LLMs) have shown their impressive capabilities in various NLP tasks, they are still under-explored in the misinformation domain. In this paper, we examine LLMs with in-context learning (ICL) for news claim verification, and find that only with 4-shot demonstration examples, the performance of several prompting methods can be comparable with previous supervised models. To further boost performance, we introduce a Hierarchical Step-by-Step (HiSS) prompting method which directs LLMs to separate a claim into several subclaims and then verify each of them via multiple questions-answering steps progressively. Experiment results on two public misinformation datasets show that HiSS prompting outperforms state-of-the-art fully-supervised approach and strong few-shot ICL-enabled baselines.
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。
