English(EN) Visual Input and Its Framing Affect Attribute-based Descriptions Produced by Large Vision-Language Models

研究发现视觉框架影响大型视觉语言模型的描述

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-17 04:00

一篇新发表在arXiv上的论文探讨了视觉输入及其框架如何影响大型视觉语言模型（LVLM）生成的基于属性的描述。研究表明，即使文本提示是通用的，图像的存在和特定框架也能显著改变LVLM的输出。例如，展示一只特定狗的图像会改变模型对犬种的描述，不同的视觉框架会导致不同的响应，包括物理术语的增加。 AI

影响强调了在评估和部署大型视觉语言模型时，需要仔细考虑视觉上下文。

排序理由该集群包含一篇详细介绍大型视觉语言模型行为研究结果的论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 11 / 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型视觉语言模型行为研究结果的论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.CV TIER_1 English(EN) · Xiaomeng Wang, Martha Larson, Zhengyu Zhao · 2026-09-17 04:00

视觉输入及其框架影响大型视觉语言模型产生的基于属性的描述

arXiv:2609.18345v1 Announce Type: new Abstract: Large vision-language models (LVLMs) are commonly used with only a single text prompt as the input, or plus an image. In this paper, we demonstrate that when the image exists, even if the text prompt is not about the specific instan…