Dynamic Decision Learning Improves Rare Disease Detection
Key Takeaways
- 1New framework improves decision making for rare disease diagnosis
- 2Enhances localization quality using large vision-language models
- 3Increases reliability of models without extensive data dependency
- 4New framework improves decision making for rare disease diagnosis • Enhances localization quality using large vision-language models • Increases reliability of models without extensive data dependency
The article presents Dynamic Decision Learning (DDL), a novel approach aimed at improving clinical abnormality grounding for rare diseases. It addresses challenges posed by data scarcity and unstable single-pass inference in supervised fine-tuning methods. By employing frozen large vision-language models (LVLMs), DDL optimizes instructions and consolidates predictions under visual perturbations, thereby enhancing localization quality and generating a consensus-based reliability score to quantify model confidence, demonstrating substantial improvements in brain imaging benchmarks.
Source
arXiv cs.CL (NLP/LLMs)https://arxiv.org/abs/2604.24972
Read original