SkinGPT-R1: Adapter-Only Dual Distillation for Efficient Dermatology Reasoning
This work addresses the need for verifiable and efficient diagnostic reasoning in dermatology, representing an incremental advancement with domain-specific applications.
The paper tackles the problem of improving diagnostic reasoning in dermatology by introducing SkinGPT-R1, a vision-language model that uses explicit chain-of-thought reasoning, achieving an average score of 4.031 out of 5 on a clinician-defined benchmark and improving over a baseline by about 41%.
We present SkinGPT-R1, a dermatology focused vision language model that makes diagnostic chain of thought reasoning explicit, step by step, and verifiable. To support skin specific reasoning, we build DermCoT, a corpus of standardized dermatologic chain of thought narratives that combines 10,000 DermEval filtered training cases with 3,000 dermatologist scored certified cases, and we define DermEval as a physician aligned six dimensional evaluator and DermBench as the corresponding benchmark for dermatologic chain of thought quality. On DermBench, across 14 general, reasoning, and medical vision language models, SkinGPT-R1 achieves an average score of 4.031 out of 5 over the six clinician defined dimensions, ranks 1st among all systems, and improves the average score over Vision-R1 by about 41%. On three dermatology classification benchmarks, SkinGPT-R1 delivers stable accuracy gains over Vision-R1 and remains competitive among strong vision language models. Ablation results further show that DermCoT based chain of thought supervision provides substantial improvements over the base model and that adding dermatology aware visual distillation yields consistent additional gains in both narrative quality and recognition.