arXiv cs.AI· Zhiwu Wang, Yichen Wu, Jinqian Yang, Yizhou Yang, Renzhen Wang, Qian Zhao, Deyu Meng·· 14 小时前AI 评分31
多模态知识编辑中的证据错位问题：诊断与 VICE 缓解方法
Diagnosing and Mitigating Evidence Misgrounding in Multimodal Knowledge Editing
AI 导读
研究提出 VICE（Visual In-Context Editing），一个基于检索的框架，将编辑存入外部记忆并通过视觉上下文演示应用，以缓解多模态知识编辑中的证据错位问题。
正文 · 原文
Abstract:Multimodal knowledge editing aims to update visually grounded facts in Multimodal Large Language Models (MLLMs) while preserving unrelated text and visual behaviors. However, standard answer-level metrics can hide evidence misgrounding: an edit may produce the target answer on the original image yet remain sensitive to incidental context rather than the intended visual evidence. To examine this issue in a controlled setting, we construct WaterBird-Edit, an analysis set that decouples bird habitat labels from background context and measures whether edited predictions remain stable when the target evidence is preserved but the background changes. Motivated by this diagnosis, we propose VICE (Visual In-Context Editing), a retrieval-based framework that stores edits in external memory and applies them through visual in-context demonstrations designed to expose task-relevant evidence. Experiments on three standard benchmarks show that VICE achieves strong lifelong editing performance, while results on WaterBird-Edit show that it substantially reduces sensitivity to the controlled background shifts. Code and dataset are available in this https URL.
| Comments: | Accepted to Findings of EMNLP 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.33075 [cs.CV] |
| (or arXiv:2610.33075v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33075 arXiv-issued DOI via DataCite |
Submission history
From: Zhiwu Wang [view email]
[v1]
Wed, 21 Oct 2026 07:00:01 UTC (605 KB)
来源：arXiv cs.AI · arxiv.org