AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MEDA: Medical-Oriented Activation Editing for Hallucination Mitigation in Medical Large Vision-Language Model

Tianbo Wang, Yuqing Ma, Lingyan Meng, Zhange Zhang, Kewei Liao, Jian Yang, Simin Li, Jinyang Guo, Xianglong Liu

ICML 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Preference tuning against hallucination

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MEDA, a medical-oriented activation editing method that mitigates hallucinations in medical large vision-language models by capturing imaging manifestations and diagnostic principles.

Problem

Medical large vision-language models (Med-LVLMs) suffer severe hallucinations that pose safety risks in clinical deployment; existing activation-editing methods lack the medical domain expertise needed to capture imaging manifestations and diagnostic principles.

Approach

Adapts activation editing to the medical domain so that the edit directions encode medical imaging manifestations and diagnostic principles, rather than generic visual features, to suppress hallucinations at inference time with minimal cost.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add QMS manifestation steering (ablation)LLaVA-Med-1.5 · IU-Xray (VQA)accuracy: 74.2 -> 81.2 (7.0%)Improved
add PDI diagnostic principle steering (ablation)LLaVA-Med-1.5 · IU-Xray (VQA)accuracy: 74.2 -> 82.5 (8.3%)Improved
combine QMS and PDI cooperatively (ablation)LLaVA-Med-1.5 · IU-Xray (VQA)accuracy: 82.5 -> 84.8Improved
add threshold control for manifestation retrieval (ablation)QMS · IU-Xray (VQA)accuracy: 80.1 -> 81.2Improved
add priority weight for entity extraction (ablation)QMS · IU-Xray (VQA)accuracy: 78.8 -> 81.2Improved
add prescribed-order sort to local evidence (ablation)PDI · IU-Xray (VQA)accuracy: 81.9 -> 82.5Improved
add scope-conditioned diagnostic template (ablation)PDI · IU-Xray (VQA)accuracy: 80.2 -> 82.5Improved
use only the raw report instead of template and sort (ablation)PDI · IU-Xray (VQA)accuracy: 82.5 -> 79.8Hurt
apply MEDA instead of best editing baseline AFTERLLaVA-Med-1.5 · IU-Xray (VQA)accuracy: 81.4 -> 84.8Improved
increase editing strength and heads beyond K=32, alpha=5 (ablation)MEDA · IU-Xray (VQA)accuracy: 84.8 -> 61.6Hurt
reduce vector-construction samples to 10 (ablation)MEDA · MIMIC-CXRaccuracy: 78.2 vs 79.4No clear effect
apply MEDA to five other LVLMsMEDA · MIMIC-CXRaccuracy: average +5.9% accuracy, +5.4% RaTEScoreImproved

Later papers that compared with this method

1 later accepted paper reports MEDA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Experimental setup

Builds on: activation editing

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy