AI RESEARCH
Retrieval-Guided Generation for Safer Histopathology Image Captioning
arXiv CS.CV
•
ArXi:2605.00893v1 Announce Type: new Generative vision-language models can produce fluent medical image captions but remain prone to hallucination, over-specific diagnostic claims, and factual inconsistency-serious issues in pathology. We investigate retrieval-guided generation (RGG) as a safer alternative, where captions are formed by summarizing expert text from visually similar cases rather than generated de novo.