English(EN) CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence

新的CiteVQA基准测试揭示了LLM中的“归因幻觉”

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 04:00

引入了一个名为CiteVQA的新基准，用于评估多模态大语言模型（MLLM）的证据归因能力。当前的文档问答（Doc-VQA）评估仅评估最终答案，忽略了模型可能引用错误来源的情况。CiteVQA要求模型在答案的同时提供元素级边界框引用，并评估两者准确性。该基准包含711个PDF文件中的1897个问题，涵盖各种领域和语言，并有一个用于生成地面真实引用（ground-truth citations）的自动化流程。测试揭示了显著的“归因幻觉”，即使是表现最好的模型，其严格归因准确率（SAA）也仅为76.0%，这凸显了当前MLLM在高风险应用中的可靠性差距。 AI

影响强调了LLM在高风险领域中一个关键的可靠性差距，需要新的评估方法来实现可信的文档智能。

排序理由该集群描述了一篇介绍用于评估AI模型基准的新学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇介绍用于评估AI模型基准的新学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Dongsheng Ma, Jiayu Li, Zhengren Wang, Yijie Wang, Jiahao Kong, Weijun Zeng, Jutao Xiao, Jie Yang, Bangrui Xu, Yuhan Wang, Bin Wang, Conghui He · 2026-10-09 04:00

CiteVQA：为可信赖文档智能进行证据归因基准测试

arXiv:2605.12882v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting evidence unchecked. This answer-only approach mask…

本文如何被排名

报道来源 [1]

CiteVQA：为可信赖文档智能进行证据归因基准测试

相关实体

相关话题