研究人员开发了CoExVQA，一个用于文档视觉问答（DocVQA）的新框架，通过分解推理过程来增强可解释性。该方法首先识别相关证据，然后定位答案区域，最后仅从该基础区域解码答案，从而实现透明验证。同时，另一项研究引入了CoVQD引导的RAG（CgRAG）框架，该框架将多模态大语言模型（MLLMs）与结构化推理和检索增强生成相结合，以提高复杂视觉问答任务的性能。 AI
影响 这些在可解释AI和多模态大语言模型整合方面的进展可能带来更可靠、可验证的文档分析和通用问答AI系统。
排序理由 该集群包含两篇arXiv论文，详细介绍了用于视觉问答任务的新框架。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2605.06058v1 Announce Type: new Abstract: Document Visual Question Answering (DocVQA) requires vision-language models to reason not only about what information in a document is relevant to a question, but also where the answer is grounded on the page. Existing DocVQA models…
Document Visual Question Answering (DocVQA) requires vision-language models to reason not only about what information in a document is relevant to a question, but also where the answer is grounded on the page. Existing DocVQA models entangle question-relevant evidence and answer …
arXiv:2605.03790v1 Announce Type: new Abstract: With advances in multimodal research and deep learning, Multimodal Large Language Models (MLLMs) have emerged as a powerful paradigm for a wide range of multimodal tasks. As a core problem in vision-language research, Visual Questio…
With advances in multimodal research and deep learning, Multimodal Large Language Models (MLLMs) have emerged as a powerful paradigm for a wide range of multimodal tasks. As a core problem in vision-language research, Visual Question Answering (VQA) has increasingly employed MLLM…