PIP-ToM 提出视角受限证据校准，提升多模态心智理论推理
Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind
一篇多模态心智理论的论文，用 GPT-4o 加上 PIP-ToM 框架，在三个 ToM 基准上准确率都冲到 92% 以上，研究智能体心理状态推理的可以看看。
论文针对多模态心智理论（ToM）任务中的证据可采纳性问题：现有 LLM 和贝叶斯方法重建全局事件轨迹，未区分客观事件与智能体可访问的证据，导致视角泄露和来源混淆。PIP-ToM 构建智能体专属证据库，与结构化心理状态声明对齐，并校准模型假设评分，同时保留底层贝叶斯推断。PIP-ToM 结合 GPT-4o 在 MuMA-ToM、MMToM-QA 和 Hi-ToM 三个基准上分别取得 92.56%、95.00% 和 95.00% 的平均准确率，超过现有 ToM 方法。
Who Knows What - and What Does It Support? Perspective-Bounded Evidence Calibration for Multimodal Theory of Mind
Theory of Mind (ToM), the ability to infer others' beliefs, goals, and intentions, is a cornerstone of social intelligence. Multimodal ToM requires inferring an agent's mental state from evidence that is available to that agent, rather than from the complete episode observed by the solver. Existing LLM-based and Bayesian model-based approaches reconstruct global event traces, yet they do not explicitly distinguish objective events from agent-admissible evidence during hypothesis evaluation. Consequently, agent-inaccessible events or semantically misaligned actions and utterances may influence the inferred belief, goal, or social intention, leading to perspective leakage and source or route confusion. We formulate this limitation as an evidence-admissibility problem: evidence should contribute to a mental-state hypothesis only when it is accessible to the relevant agent, preserves its information source, and is diagnostic of the queried mental-state variable. To operationalize this principle, we propose PIP-ToM, an evidence-admissibility interface that constructs agent-specific evidence stores, aligns them with structured mental-state claims, and calibrates model-based hypothesis scores while preserving the underlying Bayesian inference process. PIP-ToM with GPT-4o outperforms existing ToM methods across MuMA-ToM, MMToM-QA, and Hi-ToM, achieving average accuracies of 92.56%, 95.00%, and 95.00%, respectively.
