AIBearisharXiv – CS AI · Apr 147/10
🧠
Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models
Researchers evaluated domain-specific fine-tuning of vision-language models (VLMs) on medical imaging tasks and found that performance degrades significantly with task complexity, with medical fine-tuning providing no consistent advantage. The study reveals that these models exhibit fragility and high sensitivity to prompt variations, questioning the reliability of VLMs for high-stakes medical applications.
🧠 GPT-5