# RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs

Source: [RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs](<https://www.sota2.com/research/paper/68fa7b5e1e209131cea87f7a>)

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

Data updated: 2025-10-26T05:38:31.803Z

Authors: Alberto Testoni, Barbara Plank, Raquel Fern\\'andez

Published: 2024-12-18T13:25:11.000Z

## Abstract

Ambiguity resolution is key to effective communication. While humans effortlessly address ambiguity through conversational grounding strategies, the extent to which current language models can emulate these strategies remains unclear. In this work, we examine referential ambiguity in image-based question answering by introducing RACQUET, a carefully curated dataset targeting distinct aspects of ambiguity. Through a series of evaluations, we reveal significant limitations and problems of overconfidence of state-of-the-art large multimodal language models in addressing ambiguity in their responses. The overconfidence issue becomes particularly relevant for RACQUET-BIAS, a subset designed to analyze a critical yet underexplored problem: failing to address ambiguity leads to stereotypical, socially biased responses. Our results underscore the urgency of equipping models with robust strategies to deal with uncertainty without resorting to undesirable stereotypes.

## 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/2412.13835>)

[PDF](<https://arxiv.org/pdf/2412.13835.pdf>)
