CXR-PathFinder claims to outperform much larger medical vision-language models on chest X-ray reporting, using adversarial fine-tuning with clinician feedback and knowledge graph verification, but the evidence is not reproducible.
In: The Thirteenth International Confer- ence on Learning Representations (2025),https://openreview.net/forum?id= N1vYivuSKq
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Revolutionizing Radiology Workflow with Factual and Efficient CXR Report Generation
CXR-PathFinder claims to outperform much larger medical vision-language models on chest X-ray reporting, using adversarial fine-tuning with clinician feedback and knowledge graph verification, but the evidence is not reproducible.