研究多人协作中信息不对称时如何建立共同认知。
Distributed Partial Information Puzzles: Examining Common Ground Construction Under Epistemic Asymmetry
- 设计了多模态协作谜题，模拟真实信息差异场景。
- 大模型在追踪信念变化上表现不佳，仅72%准确率。
- 适合研究人机协作与认知建模的学者参考。
建立共同认知——即共享信念和相互认可的事实——是协作的基础，但在多模态、多方参与的场景中，由于参与者掌握的信息不同，这一过程仍具挑战性。本文提出分布式部分信息谜题（DPIP），一种在认知不对称下激发丰富多模态交互的协作任务。构建了一个多模态数据集，包含语音、手势和动作的同步标注与时间对齐，支持对命题内容和信念动态的推理。评估了两种共同认知建模范式：（1）使用提示工程的大语言模型（LLM），从多模态输入中推断共享信念；（2）基于动态认知逻辑（DEL）的公理化流水线，逐步完成相同任务。在标注的DPIP数据上的结果表明，现代大模型在追踪任务进展和信念状态方面面临显著挑战。
原文摘要 · Abstract (English)
Establishing common ground, a shared set of beliefs and mutually recognized facts, is fundamental to collaboration, yet remains a challenge for current AI systems, especially in multimodal, multiparty settings, where the collaborators bring different information to the table. We introduce the Distributed Partial Information Puzzle (DPIP), a collaborative construction task that elicits rich multimodal communication under epistemic asymmetry. We present a multimodal dataset of these interactions, annotated and temporally aligned across speech, gesture, and action modalities to support reasoning over propositional content and belief dynamics. We then evaluate two paradigms for modeling common ground (CG): (1) state-of-the-art large language models (LLMs), prompted to infer shared beliefs from multimodal updates, and (2) an axiomatic pipeline grounded in Dynamic Epistemic Logic (DEL) that incrementally performs the same task. Results on the annotated DPIP data indicate that it poses a challenge to modern LLMs' abilities to track both task progression and belief state.
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。