When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs

2026-08-24

AI Summary

研究通过对话互动方式改进大型视觉语言模型的视觉定位能力，解决目标信息不完整和模糊的问题。

Abstract

Visual grounding is typically evaluated as a one-shot mapping from an informative referring expression to a visual target. This formulation misses a central property of real-world reference: target information is often incomplete, ambiguous, and established through interaction. We introduce a controlled evaluation framework for interactive visual grounding in large vision-language models (LVLMs), varying how much target information is provided upfront and how much must be acquired through dialogue. Across four human-grounded visual contexts and four interaction protocols, current LVLMs perform significantly below task-level human baselines. Interaction can help when follow-up questions refine or repair an initial target description. Performance is lowest when no initial description is provided and target information must be acquired through questions, indicating that proactive question-driven grounding remains difficult. LVLMs are also poorly calibrated, often reporting confidence that exceeds their empirical accuracy. Follow-up studies confirm these patterns across varied description sources (human versus AI), reasoning efforts, repeated interactions, description providers, and visual contexts. Overall, interactive visual grounding remains an important challenge, requiring visual matching, information seeking and synthesis.

Problem

• interactive visual grounding
• large vision-language models
• incomplete target information
• ambiguous target information
• dialogue-based interaction

Innovation

• interactive visual grounding
• large vision-language models (LVLMs)
• target information acquisition
• dialogue-based refinement
• confidence calibration