cs.AI updates on arXiv.org 07月21日 12:06
When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文分析视觉语言模型在处理复杂任务时,如何通过引入多模态反事实查询数据集来解析和解决跨模态冲突,以及如何通过修改控制冲突的头模型来引导模型向内部知识或视觉输入倾斜,最终提高视觉解释的准确性。

arXiv:2507.13868v1 Announce Type: cross Abstract: Vision-language models (VLMs) increasingly leverage diverse knowledge sources to address complex tasks, often encountering conflicts between their internal parametric knowledge and external information. Knowledge conflicts can result in hallucinations and unreliable responses, but the mechanisms governing such interactions remain unknown. To address this gap, we analyze the mechanisms that VLMs use to resolve cross-modal conflicts by introducing a dataset of multimodal counterfactual queries that deliberately contradict internal commonsense knowledge. We localize with logit inspection a small set of heads that control the conflict. Moreover, by modifying these heads, we can steer the model towards its internal knowledge or the visual inputs. Finally, we show that attention from such heads pinpoints localized image regions driving visual overrides, outperforming gradient-based attribution in precision.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

视觉语言模型 跨模态冲突 模型解析 知识冲突 数据集
相关文章