提出视角化标注框架，揭示对话中看似理解实则错位的深层原因。
Grounded Misunderstandings in Asymmetric Dialogue: A Perspectivist Annotation Scheme for MapTask
- 为地图任务对话数据集设计分视角标注，区分说话人与听者对指代的理解
- 1.3万条指代表达分析显示，词汇统一后误解极少，但多重指代差异导致系统性分歧
- 适合研究对话理解、多智能体协作及大模型视角建模能力的学者使用
协作对话依赖参与者逐步建立共同认知基础，但在不对称场景中，双方可能误以为达成共识，实则指向不同实体。本文针对HCRC MapTask语料库（Anderson et al., 1991）提出一种视角化标注方案，分别记录每条指代表达中说话人与听者的认知理解，从而追踪理解如何产生、分化及修复。通过受约束的LLM标注流程，我们获得了1.3万条标注指代表达，并提供可靠性评估，进一步分析其理解状态。结果表明，一旦词汇变体被统一，完全误解极为罕见，但多重指代不一致会系统性引发分歧，揭示了表面共识下潜在的指代错位。本框架既是一个研究资源，也为分析协同对话中的非共知误解提供了分析视角，并可用于评估（视觉）大语言模型在建模视角依赖性共知方面的表现。
原文摘要 · Abstract (English)
Collaborative dialogue relies on participants incrementally establishing common ground, yet in asymmetric settings they may believe they agree while referring to different entities. We introduce a perspectivist annotation scheme for the HCRC MapTask corpus (Anderson et al., 1991) that separately captures speaker and addressee grounded interpretations for each reference expression, enabling us to trace how understanding emerges, diverges, and repairs over time. Using a scheme-constrained LLM annotation pipeline, we obtain 13k annotated reference expressions with reliability estimates and analyze the resulting understanding states. The results show that full misunderstandings are rare once lexical variants are unified, but multiplicity discrepancies systematically induce divergences, revealing how apparent grounding can mask referential misalignment. Our framework provides both a resource and an analytic lens for studying grounded misunderstanding and for evaluating (V)LLMs' capacity to model perspective-dependent grounding in collaborative dialogue.
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。