假设驱动的思维理论推理方法用于大型语言模型
Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models
AI总结：
针对LLM在无标准答案场景下推理能力不足的问题，提出基于贝叶斯思维理论框架的思维追踪算法，通过生成假设并按观察加权来追踪智能体心理状态，在多个基准上显著提升性能。
摘要：
现有的LLM推理方法在解决数学和编程问题等各种任务中展现了令人印象深刻的能力。然而，将这些方法应用于没有标准答案或基于规则的验证方法的场景——例如追踪智能体的心理状态——仍然具有挑战性。受序贯蒙特卡洛算法的启发，我们引入了思维追踪（thought-tracing），一种推理时推理算法，旨在通过生成假设并根据观察结果加权来追踪特定智能体的心理状态，而无需依赖数据集中问题的标准答案。我们的算法以贝叶斯思维理论框架为模型，利用LLM基于智能体的感知和行动来近似对其不断演变的心理状态进行概率推断。我们在多个思维理论基准上评估了思维追踪，展示了与基线LLM相比显著的性能提升。我们的实验还揭示了近期推理模型（如o3和R1）在思维理论上的有趣行为，突显了社会推理与其他领域推理的差异。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
