# Uncovering and Mitigating Transient Blindness in Multimodal Model Editing

Source: [Uncovering and Mitigating Transient Blindness in Multimodal Model Editing](<https://www.sota2.com/research/paper/691bfe366750be83fe5cefa4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-19T05:05:33.335Z

Authors: Xiaoqi Han, Ru Li, Ran Yi, Hongye Tan, Zhuomin Liang, V\\'ictor Guti\\'errez-Basulto, Jeff Z. Pan

Published: 2025-11-17T11:04:33.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.13243>)

[PDF](<https://arxiv.org/pdf/2511.13243.pdf>)
