RAcQUEt：揭示视觉LLM中被忽视的指代歧义的危险
RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs
AI总结：
本文提出RACQUET数据集以考察图像问答中的指代歧义，揭示了大型多模态语言模型在处理歧义时的局限与过度自信，并强调其易导致社会偏见，亟需稳健的不确定性处理策略。
摘要：
歧义消解是有效沟通的关键。人类能通过会话奠基策略轻松解决歧义，但当前语言模型能在多大程度上模拟这些策略仍不清晰。本研究通过引入针对歧义不同方面的精选数据集RACQUET，考察了基于图像的问答中的指代歧义。一系列评估揭示了最先进的大型多模态语言模型在解决响应歧义时存在严重局限与过度自信问题。该过度自信问题在RACQUET-BIAS子集中尤为突出，该子集旨在分析一个关键但未被充分探索的问题：未能解决歧义会导致刻板的、带有社会偏见的响应。结果强调，迫切需要为模型配备稳健策略以处理不确定性，而非诉诸不良刻板印象。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
