教视觉语言模型提问：解决视觉问题中的歧义
Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questions
AI总结：
针对VQA中用户提问歧义问题，现有方法多依赖重述问题而忽视交互反馈。本文提出ClearVQA基准，评估VLMs通过交互澄清歧义的能力，涵盖三类常见歧义及多种VQA场景。
摘要：
在视觉问答（VQA）场景中，由于用户表达习惯各异，常向视觉语言模型（VLMs）提出歧义问题。现有研究主要通过重述问题来解决此类歧义。这些方法忽视了用户与VLMs交互的内在互动本质，即歧义可通过用户反馈来澄清。然而，交互式澄清研究面临两大挑战：（1）缺乏评估VLMs通过交互解决歧义能力的基准；（2）VLMs经训练偏好回答而非提问，阻碍其寻求澄清。为克服这些挑战，我们引入ClearVQA基准，针对VQA场景中三类常见歧义类别，并涵盖多种VQA场景。
英文摘要：
In visual question answering (VQA) context, users often pose ambiguous questions to visual language models (VLMs) due to varying expression habits. Existing research addresses such ambiguities primarily by rephrasing questions. These approaches neglect the inherently interactive nature of user interactions with VLMs, where ambiguities can be clarified through user feedback. However, research on interactive clarification faces two major challenges: (1) Benchmarks are absent to assess VLMs' capacity for resolving ambiguities through interaction; (2) VLMs are trained to prefer answering rather than asking, preventing them from seeking clarification. To overcome these challenges, we introduce \textbf{ClearVQA} benchmark, which targets three common categories of ambiguity in VQA context, and encompasses various VQA scenarios.
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。
