%Aigaion2 BibTeX export van HES SO Valais Publications
%Monday 31 August 2026 12:36:07 PM

@ARTICLE{,
    author = {Long, Jieting and Li, Zhiyuan and Fan, Jianan and Liang, Zhuonan and Ma, Ao and M{\"{u}}ller, Henning and Cai, Weidong},
  keywords = {DiffusionModel, large language model, Radiology Report Generation},
     month = may,
     title = {Diversity-Augmented Diffusion Network With LLM Assistance For Radiology Report Generation},
   journal = {WWW '25: Companion Proceedings of the ACM on Web Conference 2025},
      year = {2025},
     pages = {2288-2296},
      issn = {979-8-4007-1331-6/2025/04},
       doi = {https://doi.org/10.1145/3701716.3717555},
  abstract = {Radiology report generation (RRG) is a demanding yet challenging task that involves producing multi-sentence diagnostic narratives, requiring long-form text with high diversity while addressing inherent data bias. Sentence-level diversity is therefore crucial for capturing varying diagnostic details across multiple regions of interest (ROIs) within a single report, yet it remains underexplored in the field. In this paper, we propose DADNET, a novel diffusion-based framework that leverages the inherent ability of diffusion models to generate diverse text. We make the first attempt to integrate large language models (LLMs) to bridge the inherent training-inference gap in diffusion models. Specifically, LLMs are used to draft a preliminary report, which is subsequently incorporated into the diffusion process to enhance report diversity. Additionally, we introduce a bias equalization technique using domain-specific priors to mitigate data distribution biases, improving the quality and reliability of generated reports under various scenarios. Experimental results demonstrate that DADNET outperforms existing approaches under the same non-autoregressive (NAR) mechanism and sets a new benchmark for diversity in RRG. This work underscores the importance of diversity in RRG and establishes DADNET as a pioneering framework for addressing this challenge with NAR methods.}
}