English(EN) OmniTrace: A Unified Framework for Generation-Time Source Attribution in Omni-Modal LLMs

OmniTrace框架实现全模态大语言模型溯源

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-19 04:00

研究人员开发了OmniTrace，一个新颖的框架，旨在将全模态大语言模型生成的文本归因于输入数据的特定部分。该方法在生成过程中运行，利用晚期注意力来识别文本块、图像或音频/视频片段等源单元，而无需额外的正向传递或特定于模态的调整。与传统的留一法相比，OmniTrace在效率和准确性方面表现出色，能够恢复高比例的归因信息，并与人类识别的证据高度一致。 AI

影响使全模态大语言模型的输出更加透明和可验证，这对于需要基于证据的推理的应用至关重要。

排序理由该集群包含一篇详细介绍大语言模型新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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; 该集群包含一篇详细介绍大语言模型新框架的学术论文。[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.AI TIER_1 English(EN) · Qianqi Yan, Yichen Guo, Ching-Chen Kuo, Shan Jiang, Hang Yin, Yang Zhao, Xin Eric Wang · 2026-10-19 04:00

OmniTrace：全模态大语言模型生成时溯源的统一框架

arXiv:2604.13073v2 Announce Type: replace-cross Abstract: An omni-modal language model can answer a question about a multimodal document, a recording, or a video, but it cannot show which part of the input the answer came from. Asking the model to cite its evidence yields what it…

本文如何被排名

报道来源 [1]

OmniTrace：全模态大语言模型生成时溯源的统一框架

相关实体

相关话题