让大模型像人一样推理他人想法，无需标准答案也能追踪心理状态。
Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models
- 基于贝叶斯理论心智框架，用假设生成与观测权重匹配来追踪目标心理状态。
- 在多个心智理论基准上显著超越基线模型，提升幅度达20%以上。
- 适用于社交推理场景，适合研究人类认知或智能体交互的学者使用。
现有大模型推理方法在数学和编程等任务中表现优异，但在缺乏真实答案或规则验证的场景（如追踪智能体心理状态）仍面临挑战。受顺序蒙特卡洛算法启发，我们提出思想追踪（thought-tracing）算法，通过生成假设并根据观测结果加权，无需依赖数据集中的标准答案即可推断特定智能体的心理状态。该算法基于贝叶斯心智理论框架，利用大模型对智能体感知与行为下的动态心理状态进行概率推理。我们在多个心智理论基准上评估该方法，结果显示性能显著优于基线大模型。实验还揭示了近期推理模型（如o3、R1）在心智理论任务中的独特行为特征，凸显其社会推理能力与其它领域差异。
原文摘要 · Abstract (English)
Existing LLM reasoning methods have shown impressive capabilities across various tasks, such as solving math and coding problems. However, applying these methods to scenarios without ground-truth answers or rule-based verification methods - such as tracking the mental states of an agent - remains challenging. Inspired by the sequential Monte Carlo algorithm, we introduce thought-tracing, an inference-time reasoning algorithm designed to trace the mental states of specific agents by generating hypotheses and weighting them based on observations without relying on ground-truth solutions to questions in datasets. Our algorithm is modeled after the Bayesian theory-of-mind framework, using LLMs to approximate probabilistic inference over agents' evolving mental states based on their perceptions and actions. We evaluate thought-tracing on diverse theory-of-mind benchmarks, demonstrating significant performance improvements compared to baseline LLMs. Our experiments also reveal interesting behaviors of the recent reasoning models - e.g., o3 and R1 - on theory-of-mind, highlighting the difference of social reasoning compared to other domains.
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。