English(EN) Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts

新基准 Tri-PvP 揭示全模态大语言模型的模态偏见

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

研究人员开发了 Tri-PvP，这是一个旨在暴露全模态大语言模型 (OLLM) 模态偏见的新基准。该基准通过将感知信号（如图像或音频记录）与命题信号（陈述性语句）分开，解决了先前评估中的局限性，从而更清晰地了解 OLLM 如何处理跨视觉、音频和文本的冲突信息。对五个 OLLM 的初步评估显示出显著的视觉偏见以及一种系统性不对称，即模型在视觉上偏好感知证据，而在音频上偏好命题证据。进一步分析表明，这种偏见在模型早期层即可检测到，并且难以完全缓解。 AI

影响这项研究通过识别和量化模态偏见，突出了改进多模态人工智能的关键领域，有望带来更强大、更可靠的 OLLM。

排序理由该集群描述了一篇介绍用于评估大语言模型的新颖基准的学术论文。

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; 该集群描述了一篇介绍用于评估大语言模型的新颖基准的学术论文。
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) · Yen-Ting Piao, Shu-Yun Chen, Chin-Hui Chu, Chun-Wei Chen, Shih-Yun Shan Kuan, Hung-yi Lee, Yun-Nung Chen · 2026-09-10 04:00

Tri-PvP：通过感知-命题证据冲突揭示全模态大语言模型中的模态偏见

arXiv:2609.06011v1 Announce Type: cross Abstract: Omni-modal large language models (OLLMs) jointly process vision, audio, and text, yet their modality bias under cross-modal conflict remains underexplored. Existing benchmarks conflate two distinct forms of evidence within a singl…

本文如何被排名

报道来源 [1]

Tri-PvP：通过感知-命题证据冲突揭示全模态大语言模型中的模态偏见

相关实体

相关话题