cs.CLNov 16, 2026

Seeing Isn't Resolving: Visual and Linguistic Disambiguation with Conversational Grounding

Authors: Edoardo Cecchinato, Shun Inadumi, Angel García Contreras, Giuseppe Riccardi, Koichiro Yoshino

Organizations: Signals and Interactive Systems Lab, University of Trento, Italy · The University of Osaka, Japan · Guardian Robot Project, RIKEN, Japan

Abstract

Visual grounding benchmarks usually do not consider the contextual uncertainty of real-world scenarios. In this study, we construct a novel benchmark, the Japanese evaluation for Ambiguous visual Grounding with Dialogue (JAG-D) dataset. It consists of human-robot conversational multimodal interactions covering different types of ambiguity, arising from visual and linguistic categories. We evaluate the capabilities of different state-of-the-art Visual Language Models (VLMs) for ambiguity recognition and resolution. We compare dialogue context grounding performance for visual and linguistic ambiguity resolution. Our experiments show that VLMs can substantially improve the resolution of linguistic ambiguity, especially Japanese zero anaphora, by using dialogue context. We further conduct a comparative analysis to understand whether grounding improvements arise from the semantic content of the dialogue or from its conversational structure.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding

    Oct 14, 2026Shun Inadumi, Lee Sangmyeong, Koichiro YoshinoVisual GroundingVision-Language Grounding

  2. MM-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3D Dialogue

    May 20, 2026Anna Deichler, Jim O'Regan, Fethiye Irmak Dogan +4Query ReformulationVisually Grounded Reasoning

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

    Aug 25, 2026Zhengxiang Wang, Owen RambowVLM EvaluationLarge Vision-Language Models