Prompt engineering and anatomical context significantly affect zero-shot diagnostic accuracy of pathology vision-language models, with CONCH outperforming a larger model, Quilt-LLAVA.
In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Investigating Zero-Shot Diagnostic Pathology in Vision-Language Models with Efficient Prompt Design
Prompt engineering and anatomical context significantly affect zero-shot diagnostic accuracy of pathology vision-language models, with CONCH outperforming a larger model, Quilt-LLAVA.