Saved in:
Bibliographic Details
Main Authors: Han, Xiaoqi, Li, Ru, Yi, Ran, Tan, Hongye, Liang, Zhuomin, Gutiérrez-Basulto, Víctor, Pan, Jeff Z.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.13243
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Multimodal Model Editing (MMED) aims to correct erroneous knowledge in multimodal models. Existing evaluation methods, adapted from textual model editing, overstate success by relying on low-similarity or random inputs, obscure overfitting. We propose a comprehensive locality evaluation framework, covering three key dimensions: random-image locality, no-image locality, and consistent-image locality, operationalized through seven distinct data types, enabling a detailed and structured analysis of multimodal edits. We introduce De-VQA, a dynamic evaluation for visual question answering, uncovering a phenomenon we term transient blindness, overfitting to edit-similar text while ignoring visuals. Token analysis shows edits disproportionately affect textual tokens. We propose locality-aware adversarial losses to balance cross-modal representations. Empirical results demonstrate that our approach consistently outperforms existing baselines, reducing transient blindness and improving locality by 17% on average.