Author

Mohammadsajad Abavisani

h-index 3 View on Semantic Scholar

We have 1 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Confident but Unreliable: A Behavioral Safety Audit of Vision-Language Models on Brain MRI

It is argued that medical-image VLM evaluation should report verbalized-confidence reliability, confident error, hallucination, and abstention alongside accuracy, and that medical adaptation improves tumor-presence detection without improving confidence reliability.

Amir Sabbaghziarani, Mohammadsajad Abavisani, Sergey M. Plis · 0 citations