用有限状态机让AI更懂情绪，对话更持久有效。
EmoFSM: A Finite State Machine for Emotional Support Conversation
- 用有限状态机框架让大模型自主规划对话流程
- 在多个数据集上超越主流方法，包括参数更多模型
- 适合需要长期情感支持的场景，如心理健康应用
情感支持对话（ESC）旨在通过有效对话缓解人们的情绪困扰。尽管大语言模型（LLMs）在该领域取得显著进展，但多数研究未从状态模型视角构建对话结构，导致长期满意度不足。为此，我们引入有限状态机（FSM）与大模型结合，提出EmoFSM框架。该框架使单个大模型能在每轮对话中自主规划、自我推理用户情绪、应对策略及最终回复。大量实验表明，EmoFSM在多个ESC数据集上优于多种基线方法，包括直接推理、自微调、思维链、微调以及外部支持方法，即使参数量更少也表现更优。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。