让聊天机器人具备心理理论能力，更像人一样理解彼此想法。
Enhancing Conversational Agents with Theory of Mind: Aligning Beliefs, Desires, and Intentions for Human-Like Interaction
- 用信念、欲望和意图建模人类心智，引导对话生成
- 3B和8B模型对话胜率分别达67%和63%，显著提升一致性
- 适合想做智能对话系统的研究者与开发者
基于大语言模型（LLM）的智能体自然语言交互预计将在未来长期主导。尽管人类在交流中天然具备心理理论（ToM）能力，能根据对方的心理状态调整表达，当前基于LLM的系统却存在明显局限。本研究探讨开源模型LLaMA在捕捉与保持ToM相关信息方面的表现，并检验显式操控信念、欲望与意图等组件能否增强回应的一致性。在两个LLaMA 3变体上的实验表明，引入以心理理论为导向的对齐机制可显著提升响应质量，3B与8B模型的对话胜率分别达到67%和63%。结果表明，基于心理理论的策略有助于改善基于LLM的对话智能体的对齐表现。
原文摘要 · Abstract (English)
Natural language interaction with agentic Artificial Intelligence (AI), driven by Large Language Models (LLMs), is expected to remain a dominant paradigm in the near future. While humans instinctively align their communication with mental states -- an ability known as Theory of Mind (ToM), current LLM powered systems exhibit significant limitations in this regard. This study examines the extent to which open source language models (LLaMA) can capture and preserve ToM related information and how effectively it contributes to consistent ToM reasoning in generated responses. We further investigate whether explicit manipulation of ToM related components, such as beliefs, desires, and intentions, can enhance response alignment. Experiments on two LLaMA 3 variants demonstrate that incorporating ToM informed alignment improves response quality, achieving win rates of 67 and 63 percent for the 3B and 8B models, respectively. These findings highlight the potential of ToM driven strategies to improve alignment in LLM based conversational agents.
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。