PulseAugur
中
实时 11:52:07
English(EN) MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

新方法MultAttnAttrib提高了多模态归因的准确性

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员推出了一种新颖的方法MultAttnAttrib，用于在多模态问答系统中生成归因，而无需额外训练。该方法利用模型的预填充通道、特定的注意力头和校准的阈值来精确定位文档中的证据。为了评估其有效性，创建了一个名为MultAttrEval的新基准数据集，其中包含基于多模态来源的答案的细粒度归因。MultAttnAttrib在现有归因方法（包括基于提示的方法）方面表现出优越的性能，甚至能与GPT 5.4等先进模型相媲美，同时显著降低了推理延迟。 AI

影响 通过提高答案归因的准确性和效率，增强了基于QA系统的信任和安全性。

排序理由 该集群描述了一篇介绍用于问答多模态归因的新颖方法和数据集的研究论文。[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 2 个来源。 我们如何撰写摘要 →

新方法MultAttnAttrib提高了多模态归因的准确性

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi, Sai Soorya Rao Veeravalli, Trang Nguyen, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Koustava Goswami, Samyadeep Basu ·

    MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

    arXiv:2607.01420v1 Announce Type: cross Abstract: As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal attributions have been explored in depth, the mult…

  2. arXiv cs.CL TIER_1 English(EN) · Samyadeep Basu ·

    MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering

    As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal attributions have been explored in depth, the multimodal setting remains relatively under-researched…

相关实体

相关话题