🚨 Preprint out — Clinical Contrastive Decoding！
“CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding”. The preprint is now available.
For detailed model information and source code, please visit our Project Page: CCD
Overview
Multimodal large language models (MLLMs) have advanced radiology tasks by combining image and text understanding, but can sometimes produce inaccurate or unsupported clinical statements—so-called medical hallucinations. We introduce Clinical Contrastive Decoding (CCD), an inference-time method that leverages structured clinical signals (for example, symptom-level probabilities from specialist classifiers) to refine token-level logits during generation. CCD is designed to be applied without modifying base model weights or requiring external retrieval. In our evaluations on datasets such as MIMIC-CXR and IU-Xray, CCD yields consistent improvements in clinical metrics (for example, up to +17% RadGraph-F1 on MIMIC-CXR), reducing unsupported mentions while preserving overall fluency.
Key Resources
- Interactive Demo — Try
CCDonline - GitHub Repository — Explore the
CCDproject on GitHub
