QuestGen：面向事实核查应用的问题生成方法的有效性研究
QuestGen: Effectiveness of Question Generation Methods for Fact-Checking Applications
AI总结：
本文提出QuestGen，通过数据增强微调较小生成模型自动分解事实核查声明为问题，性能超越大模型最多8%，且机器生成问题的证据检索效果在部分场景优于人工问题。
摘要：
验证事实核查声明即使对人类而言也是一项重大挑战。近期方法表明，将声明分解为相关问题以收集证据能够提高事实核查流程的效率。在本文中，我们提供实证证据，表明这种问题分解可以被有效自动化。我们证明，使用来自多个数据集的数据增强对问题生成任务进行微调的较小生成模型，其性能比大型语言模型高出最多8%。令人惊讶的是，在某些情况下，使用机器生成的问题检索到的证据在事实核查方面显著优于从人工编写的问题中获得的证据。我们还对分解后的问题进行了人工评估，以评估所生成问题的质量。
英文摘要：
Verifying fact-checking claims poses a significant challenge, even for humans. Recent approaches have demonstrated that decomposing claims into relevant questions to gather evidence enhances the efficiency of the fact-checking process. In this paper, we provide empirical evidence showing that this question decomposition can be effectively automated. We demonstrate that smaller generative models, fine-tuned for the question generation task using data augmentation from various datasets, outperform large language models by up to 8%. Surprisingly, in some cases, the evidence retrieved using machine-generated questions proves to be significantly more effective for fact-checking than that obtained from human-written questions. We also perform manual evaluation of the decomposed questions to assess the quality of the questions generated.
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。
