Grounded Misunderstandings in Asymmetric Dialogue: A Perspectivist Annotation Scheme for MapTask
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 13 of its 48 references that are in the map. First posted on arXiv 5 Nov 2025.
Builds on
13 of 48 references.
References · 13
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
- 2016Modeling Context in Referring Expressionscited by 1,063
- 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 215
- 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 197
- 2024Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguitiescited by 59
- 2025Flexible and Efficient Grammar-Constrained Decodingcited by 43
- 2025Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulationcited by 42
- 2019A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Contextcited by 35
- 2023"You Are An Expert Linguistic Annotator": Limits of LLMs as Analyzers of Abstract Meaning Representationcited by 15
- 2024Common Ground Tracking in Multimodal Dialoguecited by 13
- 2025LVLMs are Bad at Overhearing Human Referential Communicationcited by 8
Built on by
Citing papers per year: 2026: 2.
2 papers.