概念思维链激发大语言模型的日常对话能力
Chain-of-Conceptual-Thought Elicits Daily Conversation in Large Language Models
AI总结：
针对思维链在开放域任务性能受限的问题，本文提出概念思维链提示范式，通过分层概念引导生成，在对话任务上优于多个提示基线方法。
摘要：
思维链（CoT）被广泛应用于提升大语言模型在数学、编程和推理任务中的能力，但在缺乏明确定义的推理步骤或逻辑转换的开放域任务中，其性能存在局限。为缓解该问题，我们提出一种基于提示的新范式——概念思维链（CoCT），引导大语言模型先生成概念标签，再围绕概念补全详细内容。为鼓励这种分层思维模式，我们用情绪、策略和话题实现概念落地。我们在日常对话与情感支持对话场景开展实验，覆盖域内和域外概念设置的任务。自动评估、人工评估和基于大语言模型的评估结果显示，CoCT性能优于self-refine、ECoT、SoT、RAG等多种基于提示的基线方法，为适配更广泛任务的大语言模型提示范式提供了潜在解决方案。
英文摘要：
Chain-of-Thought (CoT) is widely applied to enhance the LLM capability in math, coding and reasoning tasks. However, its performance is limited for open-domain tasks, when there are no clearly defined reasoning steps or logical transitions. To mitigate such challenges, we propose a new prompt-based paradigm called Chain of Conceptual Thoughts (CoCT), which suggests the LLM first to produce the tag of concepts, then complete the detailed content following the concept. To encourage this hierarchical way of thinking, we implement the concepts with emotions, strategies and topics. We experiment with this paradigm in daily and emotional support conversations, covering tasks with both in-domain and out-of-domain concept settings. Automatic, human, and LLM-based evaluations reveal that CoCT surpasses several prompt-based baselines such as self-refine, ECoT, SoT and RAG, suggesting a potential solution of LLM prompting paradigm for a wider scope of tasks.
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。
