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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use reference-free DermEval evaluator instead of reference-based DermBench judge | physician-aligned scoring · Alignment test (500 DermNet images, 9 models) | average MAE vs physician: 0.363 -> 0.178 | Improved |
| use DermEval instead of DermBench | physician-aligned scoring · Alignment test (500 DermNet images, 9 models) | Accuracy MAE: 0.251 -> 0.117 | Improved |
| use DermEval instead of DermBench | physician-aligned scoring · Alignment test (500 DermNet images, 9 models) | Clinical Coverage MAE: 0.456 -> 0.152 | Improved |
| compare DermEval with DermBench on model scores | model ranking on DermNet · DermNet benchmark (9 MLLMs) | score agreement: differ by no more than 0.05 | No clear effect |
| evaluate frequent prototypical class (Eczema) instead of Vasculitis | DermEval · Class-wise alignment | Accuracy MAE: 0.138 -> 0.088 | Improved |
| evaluate Acne and Rosacea instead of Systemic Disease | DermEval · Class-wise alignment | Reasoning Coherence MAE: 0.277 -> 0.192 | Improved |
Closest papers by meaning
- DermaCon-IN: A Multiconcept-Annotated Dermatological Image Dataset of Indian Skin Disorders for Clinical AI Research (NeurIPS 2025 · similarity 0.87)
- Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback (NeurIPS 2025 · similarity 0.84)
- Medical thinking with multiple images (ICLR 2026 · similarity 0.84)
- DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis? (NeurIPS 2025 · similarity 0.83)
- CUPCase: Clinically Uncommon Patient Cases and Diagnoses Dataset (AAAI 2025 · similarity 0.83)
- BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature (CVPR 2025 · similarity 0.83)
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.
