# Measuring How (Not Just Whether) VLMs Build Common Ground

Source: [Measuring How (Not Just Whether) VLMs Build Common Ground](<https://www.sota2.com/research/paper/68fa7b261e209131cea86df5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:34:43.561Z

Authors: Saki Imai, Mert \\.Inan, Anthony Sicilia, Malihe Alikhani

Published: 2025-09-04T01:43:49.000Z

## Abstract

Large vision language models (VLMs) increasingly claim reasoning skills, yet current benchmarks evaluate them in single-turn or question answering settings. However, grounding is an interactive process in which people gradually develop shared understanding through ongoing communication. We introduce a four-metric suite (grounding efficiency, content alignment, lexical adaptation, and human-likeness) to systematically evaluate VLM performance in interactive grounding contexts. We deploy the suite on 150 self-play sessions of interactive referential games between three proprietary VLMs and compare them with human dyads. All three models diverge from human patterns on at least three metrics, while GPT4o-mini is the closest overall. We find that (i) task success scores do not indicate successful grounding and (ii) high image-utterance alignment does not necessarily predict task success. Our metric suite and findings offer a framework for future research on VLM grounding.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.03805>)

[PDF](<https://arxiv.org/pdf/2509.03805.pdf>)
