English(EN) Feature Competition and Its Representational Origins in Vision Language Models: Evidence from the Stroop Paradigm

视觉-语言模型在斯特鲁普任务实验中表现出文本偏见

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-12 04:00

研究人员改编了心理学中的斯特鲁普范式，以研究视觉-语言模型（VLMs）如何处理具有冲突特征的图像。当呈现文本和颜色不一致的图像时，VLMs在响应中始终优先考虑文本特征而非颜色特征。对模型嵌入空间的进一步分析显示，文本线索的表征比颜色线索更强、更清晰，这解释了这种偏见，并预测了干预文本相关特征的容易程度。 AI

影响强调了VLMs中的特征显著性如何影响下游应用的性能，表明需要更深入地理解表征偏见。

排序理由学术论文，详细介绍了应用于AI模型的新实验方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 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: 10 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了应用于AI模型的新实验方法。[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。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Nurb\"uke Teker, Rui Xiao, Zeynep Akata, Shuchen Wu · 2026-10-12 04:00

视觉语言模型中的特征竞争及其表征起源：来自斯特鲁普范式的证据

arXiv:2610.12650v1 Announce Type: new Abstract: When you ask a vision-language model (VLM) a question with an image, it answers your question based on the image. But to act means to choose: saying one thing means choosing to respond not say another. This becomes an issue when the…

本文如何被排名

报道来源 [1]

视觉语言模型中的特征竞争及其表征起源：来自斯特鲁普范式的证据

相关实体

相关话题