CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation

arXiv:2604.10410v1 Announce Type: new Abstract: Interpreting chest X-rays is inherently challenging due to the overlap between anatomical structures and the subtle presentation of many clinically significant pathologies, making accurate diagnosis time-consuming even for experienced radiologists. Recent radiology-focused foundation models, such as LLaVA-Rad and Maira-2, have positioned multi-modal large language models (MLLMs) at the forefront of automated radiology report generation (RRG). However, despite these advances, current foundation models generate reports in a single forward pass. This decoding strategy diminishes attention to visual tokens and increases reliance on language priors as generation proceeds, which in turn introduces spurious pathology co-occurrences in the generated reports. To mitigate these limitations, we propose Category-Wise Contrastive Decoding (CWCD), a novel and modular framework designed to enhance structured radiology report generation (SRRG). Our approach introduces category-specific parameterization and generates category-wise reports by contrasting normal X-rays with masked X-rays using category-specific visual prompts. Experimental results demonstrate that CWCD consistently outperforms baseline methods across both clinical efficacy and natural language generation metrics. An ablation study further elucidates the contribution of each architectural component to overall performance.

Related

• SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
• Chronological Contrastive Learning: Few-Shot Progression Assessment in Irreversible Diseases
• 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
• Efficient Process Reward Modeling via Contrastive Mutual Information
• Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs

Source: arXiv cs.AI | 2026-04-14