CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding

Xi Zhang, Zaiqiao Meng, Jake Lever, Edmond S. L. Ho

Keywords: Radiology AI, Chest X-ray, Multimodal Large Language Models, Hallucination Mitigation, Decoding Strategy

TL;DR: We propose Clinical Contrastive Decoding, a training-free and retrieval-free inference strategy that mitigates medical hallucinations in radiology MLLMs by integrating task-specific expert model guidance through a dual-stage contrastive mechanism.

Abstract: Multimodal large language models (MLLMs) have recently achieved remarkable progress in radiology by integrating visual perception with natural language understanding. However, they often generate clinically unsupported descriptions, known as medical hallucinations, which pose serious risks in medical applications that demand accuracy and image-grounded outputs. Through empirical analysis, we find that prompt-induced hallucinations remain prevalent in radiology MLLMs, largely due to over-sensitivity to clinical sections. To address this, we introduce **C**linical **C**ontrastive **D**ecoding (**CCD**), a *training-free* and *retrieval-free* inference framework that integrates structured clinical signals from task‑specific radiology expert models. CCD introduces a dual-stage contrastive mechanism to refine token-level logits during generation, thereby enhancing clinical fidelity without modifying the base MLLM. Experiments on three datasets and multiple models demonstrate that CCD consistently improves overall performance on radiology report generation (RRG). On the MIMIC-CXR dataset, it yields up to a **2.78** absolute improvement in RadGraph-F1 when applied to state-of-the-art RRG models. Our approach provides a lightweight solution for mitigating medical hallucinations, effectively bridging expert models and MLLMs in radiology.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 9239