Entity · dataset

HCRC MapTask

datasetactiveprovisionalhcrc-maptask-9fc92f5b·1 events·first seen 6d ago

Aliases: HCRC MapTask

Co-occurring entities

Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue Qwen3-4B-Instruct

More like this (12)

Map Task LangMAP KSAA-2026 Shared Task TPC-H HMMT 2026 H-RePlan Match Task to Objective (MTO)Functional Maps G-RRM eGeMAPS MAGMaR 2026 Shared Task Map-Reduce Decomposition

Recent events (1)

5arXiv · cs.CL·6d ago·source ↗

VLMs overestimate common ground in asymmetric dialogue, conflating potential with established shared understanding

A new arXiv paper investigates whether vision-language models can distinguish between what could be shared versus what has actually been established as shared between dialogue participants. Using 13,077 annotated reference expressions from HCRC MapTask dialogues, the authors find that VLMs systematically over-predict alignment when given task-relevant map content—whether presented visually or as text—suggesting the bias stems from static referential cues rather than tracking grounding through dialogue history. The effect is observed most strongly in Qwen3-VL-8B-Instruct and replicated across four additional models from two architecture families, revealing a fundamental limitation in how current VLMs model collaborative dialogue.

Evaluation and Benchmarking Multimodal Progress Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue HCRC MapTask Qwen3-4B-Instruct