用动态信念图提升大模型在危机中的心理推理能力
Learning Dynamic Belief Graphs for Theory-of-mind Reasoning
- 构建动态信念图，追踪信念随时间演变及相互依赖
- 在真实灾荒撤离数据上，行动预测准确率显著提升
- 适合需要理解人类决策心理的高风险场景应用
基于大语言模型的理论心智（ToM）推理需推断人们隐含、动态变化的信念如何影响其在不确定性下的行为，尤其在灾害响应、紧急医疗和人机协同等高风险场景中。现有方法或直接提示模型，或使用静态独立的潜在状态模型，常导致认知模型不连贯、动态推理能力弱。本文提出一种结构化认知轨迹模型，将心智状态表示为动态信念图，联合推断隐含信念、学习其时变依赖关系，并关联信念演化与信息获取及决策。模型创新包括：(i) 将文本化的概率陈述映射为一致的概率图更新；(ii) 采用能量基因子图表示信念间依赖；(iii) 基于ELBO的目标函数捕捉信念积累与延迟决策。在多个真实灾荒撤离数据集上，模型显著提升行动预测性能，并恢复出符合人类推理的可解释信念轨迹，为高不确定性环境中增强大模型理论心智提供原则性模块。
原文摘要 · Abstract (English)
Theory of Mind (ToM) reasoning with Large Language Models (LLMs) requires inferring how people's implicit, evolving beliefs shape what they seek and how they act under uncertainty -- especially in high-stakes settings such as disaster response, emergency medicine, and human-in-the-loop autonomy. Prior approaches either prompt LLMs directly or use latent-state models that treat beliefs as static and independent, often producing incoherent mental models over time and weak reasoning in dynamic contexts. We introduce a structured cognitive trajectory model for LLM-based ToM that represents mental state as a dynamic belief graph, jointly inferring latent beliefs, learning their time-varying dependencies, and linking belief evolution to information seeking and decisions. Our model contributes (i) a novel projection from textualized probabilistic statements to consistent probabilistic graphical model updates, (ii) an energy-based factor graph representation of belief interdependencies, and (iii) an ELBO-based objective that captures belief accumulation and delayed decisions. Across multiple real-world disaster evacuation datasets, our model significantly improves action prediction and recovers interpretable belief trajectories consistent with human reasoning, providing a principled module for augmenting LLMs with ToM in high-uncertainty environment. https://anonymous.4open.science/r/ICML_submission-6373/
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。