思维线索：解开混乱上下文之谜
Thread of Thought Unraveling Chaotic Contexts
AI总结：
针对大型语言模型在混乱上下文中遗漏细节的问题，提出借鉴人类认知的“思维线索”策略，作为即插即用模块系统分段分析上下文并选择相关信息，在PopQA、EntityQ及MTCR数据集上显著提升推理性能。
摘要：
大型语言模型（LLMs）在自然语言处理领域开启了变革时代，在文本理解和生成相关任务中表现出色。然而，当面对混乱上下文（例如，干扰项而非冗长的无关上下文）时，它们会遇到困难，导致在混乱上下文中无意中遗漏某些细节。针对这些挑战，我们引入了“思维线索”（ThoT）策略，该策略借鉴了人类认知过程。ThoT系统性地对扩展上下文进行分段和分析，同时熟练地选择相关信息。该策略作为一个通用的“即插即用”模块，可与各种LLMs和提示技术无缝集成。在实验中，我们利用PopQA和EntityQ数据集，以及我们收集的多轮对话回复数据集（MTCR），证明与其他提示技术相比，ThoT显著提高了推理性能。
英文摘要：
Large Language Models (LLMs) have ushered in a transformative era in the field of natural language processing, excelling in tasks related to text comprehension and generation. Nevertheless, they encounter difficulties when confronted with chaotic contexts (e.g., distractors rather than long irrelevant context), leading to the inadvertent omission of certain details within the chaotic context. In response to these challenges, we introduce the "Thread of Thought" (ThoT) strategy, which draws inspiration from human cognitive processes. ThoT systematically segments and analyzes extended contexts while adeptly selecting pertinent information. This strategy serves as a versatile "plug-and-play" module, seamlessly integrating with various LLMs and prompting techniques. In the experiments, we utilize the PopQA and EntityQ datasets, as well as a Multi-Turn Conversation Response dataset (MTCR) we collected, to illustrate that ThoT significantly improves reasoning performance compared to other prompting techniques.
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。
