EmoFSM：一种用于情感支持对话的有限状态机
EmoFSM: A Finite State Machine for Emotional Support Conversation
AI总结：
针对情感支持对话中长期满意度不足的问题，提出EmoFSM框架，利用有限状态机引导大语言模型进行规划与自我推理，在多个数据集上优于多种基线方法。
摘要：
情感支持对话旨在通过有效对话缓解人们的情感困扰。尽管大语言模型在ESC方面取得了显著进展，但大多数研究可能未从状态模型角度定义图，从而为长期满意度提供了次优解决方案。为解决此问题，我们利用有限状态机在LLM上提出名为EmoFSM的框架。我们的框架允许单个LLM在ESC期间引导规划，并在每个对话轮次中自我推理求助者的情绪、支持策略以及最终回应。在ESC数据集上的大量实验表明，EmoFSM优于许多基线方法，包括直接推理、自我微调、思维链、微调和外部支持方法，甚至那些参数更多的模型。
英文摘要：
Emotional support conversation (ESC) aims to alleviate people's emotional distress through effective conversations. Although large language models (LLMs) have made remarkable progress in ESC, most of these studies may not define the diagram from a state-model perspective, thereby providing a suboptimal solution for long-term satisfaction. To address such an issue, we leverage the Finite State Machine (FSM) on LLMs, and propose a framework called EmoFSM. Our framework allows a single LLM to bootstrap the planning during ESC, and self-reason the seeker's emotion, support strategy, and the final response upon each conversation turn. Substantial experiments in ESC datasets suggest that EmoFSM outperforms many baselines, including direct inference, self-fine, chain of thought, finetuning, and externally supported methods, even those with many more parameters.
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。
