论文概要
研究领域: ML 作者: Nanxu Gong, Zixin Chen, Haotian Li 发布时间: 2025-05-15 arXiv: 2505.10890
中文摘要
提升大语言模型（LLM）的心智理论（ToM）能力对AI模型与人类之间的有效社交互动至关重要。然而，现有基准通常通过故事阅读、第三人称视角的多选题来衡量ToM能力提升，却忽略了人机交互（HAI）的第一人称、动态和开放式本质。为直接检验ToM改进技术如何使HAI交互受益，我们首先提出了交互式ToM评估新范式，兼具视角和指标的转变。随后，我们遵循该范式，对四种代表性ToM增强技术进行了系统研究，使用四个真实数据集和一项用户研究，涵盖目标导向任务（如编程、数学）和体验导向任务（如咨询）。我们的发现揭示，静态基准上的改进并不总能转化为动态HAI交互中的更好表现。本文对ToM评估提供了关键洞见，表明在开发面向HAI共生的下一代社交感知LLM时，基于交互的评估是必要的。
原文摘要
Improving the Theory of Mind (ToM) capability of Large Language Models (LLMs) is crucial for effective social interactions between these AI models and humans. However, the existing benchmarks often measure ToM capability improvement through story-reading, multiple-choice questions from a third-person perspective, while ignoring the first-person, dynamic, and open-ended nature of human-AI (HAI) interactions. To directly examine how ToM improvement techniques benefit HAI interactions, we first proposed the new paradigm of interactive ToM evaluation with both perspective and metric shifts. Next, following the paradigm, we conducted a systematic study of four representative ToM enhancement techniques using both four real-world datasets and a user study, covering both goal-oriented tasks (e.g.,...
--- *自动采集于 2026-05-19*
#论文 #arXiv #ML #小凯