# Evaluating and Understanding Model Editing for Medical Vision Language Models

arXiv: https://arxiv.org/abs/2607.05310 · HTML: https://mlsanity.com/paper/2607.05310/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering](https://mlsanity.com/paper/2102.09542/) (2021)
- [Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors](https://mlsanity.com/paper/2211.11031/) (2022)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [Knowledge Editing for Large Language Models: A Survey](https://mlsanity.com/paper/2310.16218/) (2023)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generation](https://mlsanity.com/paper/2411.05085/) (2024)
- [The Mirage of Model Editing: Revisiting Evaluation in the Wild](https://mlsanity.com/paper/2502.11177/) (2025)
- [Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, and LLaMA](https://mlsanity.com/paper/2512.12812/) (2025)
- [MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge](https://mlsanity.com/paper/2502.19870/) (2025)
- [On Domain-Adaptive Post-Training for Multimodal Large Language Models](https://mlsanity.com/paper/2411.19930/) (2024)
- [BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing](https://mlsanity.com/paper/2505.01343/) (2025)
- [MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation](https://mlsanity.com/paper/2406.11566/) (2024)
- [SurgXBench: Explainable Vision-Language Model Benchmark for Surgery](https://mlsanity.com/paper/2505.10764/) (2025)
- [Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2505.19498/) (2025)
- [MedMKEB: A Comprehensive Knowledge Editing Benchmark for Medical Multimodal Large Language Models](https://mlsanity.com/paper/2508.05083/) (2025)

## Abstract (arXiv)

Model editing promises a fast, targeted way to correct post-deployment mistakes in medical vision-language models (VLMs) without costly retraining. However, existing multimodal model editing benchmarks focus on general-purpose tasks and do not reflect realistic clinical domain requirements and variability. To address this, we introduce M3Bench, a clinically grounded benchmark for multimodal model editing that evaluates whether an edit remains reliable, precise, and generalizable under the challenges of image and text variation, modality and protocol shifts, clinical knowledge composition, and temporal progression. M3Bench contains 16,276 questions spanning diverse anatomy, modalities, and specialties, and supports both single and sequential edits. By evaluating 4 representative editors across 6 medical and general VLMs, we find that no method excels across all criteria. Gradient-based editors achieve strong transfer but suffer from catastrophic locality violations, whereas memory-based methods preserve locality but lack compositional generality and exhibit high backbone-dependent hyperparameter sensitivity. We further attribute these failures to the latent space geometry of VLMs and how different editing methods shift its landscape. Overall, M3Bench establishes a rigorous clinical stress test for multimodal model editing and offers actionable guidance for safer post-deployment adaptation. The benchmark is publicly available at https://github.com/BioMed-AI-Lab-U-Michgan/M3Bench .