混沌背景下的思维线索展开

摘要

大型语言模型（LLMs）已经引领了自然语言处理领域的变革时代，在文本理解和生成相关任务方面表现出色。然而，当面对混乱语境（例如，干扰因素而非长篇无关上下文）时，它们会遇到困难，导致在混乱语境中无意中省略了某些细节。针对这些挑战，我们引入了“思维线索”（ThoT）策略，灵感来源于人类认知过程。ThoT系统地分割和分析扩展语境，同时熟练选择相关信息。该策略作为一种多功能的“即插即用”模块，可以与各种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），以说明与其他提示技术相比，ThoT显著改善了推理性能。

English

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.

混沌背景下的思维线索展开

Thread of Thought Unraveling Chaotic Contexts

摘要

Support