使用程序引导推理对复杂声明进行事实核查
Fact-Checking Complex Claims with Program-Guided Reasoning
AI总结：
本文提出ProgramFC模型，通过大语言模型生成推理程序将复杂声明分解为子任务并逐一执行，兼具解释性与数据效率，在两个数据集上优于七个基线。
摘要：
对现实世界的声明进行事实核查通常需要收集多条证据并应用复杂的多步推理。在本文中，我们提出了Program-Guided Fact-Checking (ProgramFC)，一种新颖的事实核查模型，该模型将复杂声明分解为更简单的子任务，这些子任务可以使用一个共享的专用函数库来解决。我们首先利用大型语言模型的上下文学习能力生成推理程序来引导验证过程。随后，我们通过将每个子任务委托给相应的子任务处理器来执行该程序。这一过程使我们的模型既具解释性又具数据效率，为其推理过程提供了清晰的解释，并且只需最少的训练数据。我们在两个具有挑战性的事实核查数据集上评估了ProgramFC，结果表明，在不同的证据可用性设置下，它的表现优于七个事实核查基线，并且其显式输出的程序有利于人工调试。我们的代码和数据已在https://github.com/mbzuai-nlp/ProgramFC公开发布。
英文摘要：
Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning. In this paper, we present Program-Guided Fact-Checking (ProgramFC), a novel fact-checking model that decomposes complex claims into simpler sub-tasks that can be solved using a shared library of specialized functions. We first leverage the in-context learning ability of large language models to generate reasoning programs to guide the verification process. Afterward, we execute the program by delegating each sub-task to the corresponding sub-task handler. This process makes our model both explanatory and data-efficient, providing clear explanations of its reasoning process and requiring minimal training data. We evaluate ProgramFC on two challenging fact-checking datasets and show that it outperforms seven fact-checking baselines across different settings of evidence availability, with explicit output programs that benefit human debugging. Our codes and data are publicly available at https://github.com/mbzuai-nlp/ProgramFC.
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。
