$π$-CoT：基于Prolog初始化的多跳问答链式思维提示法
$π$-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering
AI总结：
$π$-CoT通过结合逻辑编程与语言模型，提升多跳问答性能，优于传统RAG和CoT方法。
摘要：
链式思维（CoT）提示显著增强了大语言模型（LLMs）的问题解决能力，但仍然难以处理复杂的多跳问题，常常陷入循环推理模式或完全偏离逻辑路径。这一局限性在检索增强生成（RAG）设置中尤为突出，其中获取正确的上下文至关重要。我们引入了Prolog初始化的链式思维（$π$-CoT），一种结合逻辑编程结构严谨性与语言模型灵活性的新提示策略。$π$-CoT将多跳问题重新表述为分解为单跳子查询的Prolog查询。这些子查询依次解决，生成中间产物，随后用于初始化后续的CoT推理过程。大量实验表明，$π$-CoT在多跳问答基准测试中显著优于标准RAG和上下文CoT。
英文摘要：
Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with complex multi-hop questions, often falling into circular reasoning patterns or deviating from the logical path entirely. This limitation is particularly acute in retrieval-augmented generation (RAG) settings, where obtaining the right context is critical. We introduce Prolog-Initialized Chain-of-Thought ($π$-CoT), a novel prompting strategy that combines logic programming's structural rigor with language models' flexibility. $π$-CoT reformulates multi-hop questions into Prolog queries decomposed as single-hop sub-queries. These are resolved sequentially, producing intermediate artifacts, with which we initialize the subsequent CoT reasoning procedure. Extensive experiments demonstrate that $π$-CoT significantly outperforms standard RAG and in-context CoT on multi-hop question-answering benchmarks.
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。
