AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic Narratives

Yuhao Shen, Jiahe Qian, Zhangtianyi Chen, Juexiao Zhou

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use reference-free DermEval evaluator instead of reference-based DermBench judgephysician-aligned scoring · Alignment test (500 DermNet images, 9 models)average MAE vs physician: 0.363 -> 0.178Improved
use DermEval instead of DermBenchphysician-aligned scoring · Alignment test (500 DermNet images, 9 models)Accuracy MAE: 0.251 -> 0.117Improved
use DermEval instead of DermBenchphysician-aligned scoring · Alignment test (500 DermNet images, 9 models)Clinical Coverage MAE: 0.456 -> 0.152Improved
compare DermEval with DermBench on model scoresmodel ranking on DermNet · DermNet benchmark (9 MLLMs)score agreement: differ by no more than 0.05No clear effect
evaluate frequent prototypical class (Eczema) instead of VasculitisDermEval · Class-wise alignmentAccuracy MAE: 0.138 -> 0.088Improved
evaluate Acne and Rosacea instead of Systemic DiseaseDermEval · Class-wise alignmentReasoning Coherence MAE: 0.277 -> 0.192Improved

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