让智能体理解人对它的误解，从而更好沟通。
What Do You Think I Think? Accounting for Human Beliefs Using Second-Order Theory of Mind
- 用二阶心智理论建模人类错误信念的形成过程。
- 实验显示反馈信息量提升，用户认为指导更实用。
- 适合人机交互、教育机器人等需理解认知偏差的场景。
智能体与人的实际知识与对方认为的知识之间存在差异，可能阻碍互动。若智能体能识别此类差异，便可通过反馈加以调整，提升当前及未来交互效果。本文以I-POMDP为框架，引入二阶心智理论（ToM-2），使智能体能够建模人类对智能体的错误信念及其背后认知偏差与启发式策略（CBH）的演化过程。由此，智能体可在互动中检测到CBH的影响，并自适应生成考虑这些偏差的反馈。一次面对面用户研究显示，采用ToM-2的学习者能有效应对教师的CBH，显著提升教师行为的信息量；主观评估也表明，用户认为该学习者的反馈更具实用性。
原文摘要 · Abstract (English)
Discrepancies between an agent's actual knowledge and what a person thinks the agent knows can hinder interactions. If an agent could detect such discrepancies, it could provide feedback to account for them and improve current and future interactions. Using the I-POMDP as a framework for a second-order Theory of Mind (ToM-2), this work endows an agent with the ability to model the evolution of a person's erroneous beliefs about an agent and the cognitive biases and heuristics (CBH) from which they arise. In doing so, the agent can detect when CBH might be at play during an interaction and adaptively generate feedback that accounts for them. An in-person user study shows how a ToM-2 learner can account for the effects of a teacher's CBH to significantly improve the informativeness of teacher actions, and subjective results suggest people find the ToM-2 learner's feedback more useful.
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。