Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models

arXiv:2604.09841v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly adapted through domain-specific fine-tuning, yet it remains unclear whether this improves reasoning beyond superficial visual cues, particularly in high-stakes domains like medicine. We evaluate four paired open-source VLMs (LLaVA vs. LLaVA-Med; Gemma vs. MedGemma) across four medical imaging tasks of increasing difficulty: brain tumor, pneumonia, skin cancer, and histopathology classification. We fi