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.

翻译：情感支持对话旨在通过有效对话缓解人们的情绪困扰。尽管大语言模型在情感支持对话领域取得了显著进展，但多数研究可能未从状态模型视角定义对话图式，从而在长期满意度方面提供次优解决方案。为解决该问题，我们将有限状态机与大语言模型相结合，提出EmoFSM框架。该框架使单一LLM能够自主规划对话流程，并在每轮对话中自我推理求助者的情绪状态、支持策略及最终回应。在情感支持对话数据集上的大量实验表明，EmoFSM优于多种基线方法，包括直接推理、自微调、思维链、微调及外部支持方法，甚至超越参数规模更大的模型。