@inproceedings{he-etal-2025-pfedrag,
    title = "p{F}ed{RAG}: A Personalized Federated Retrieval-Augmented Generation System with Depth-Adaptive Tiered Embedding Tuning",
    author = "He, Hangyu  and
      Yuan, Xin  and
      Wu, Kai  and
      Liu, Ren Ping  and
      Ni, Wei",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.769/",
    doi = "10.18653/v1/2025.findings-emnlp.769",
    pages = "14255--14268",
    ISBN = "979-8-89176-335-7",
    abstract = "Large Language Models (LLMs) can undergo hallucinations in specialized domains, and standard Retrieval-Augmented Generation (RAG) often falters due to general-purpose embeddings ill-suited for domain-specific terminology. Though domain-specific fine-tuning enhances retrieval, centralizing data introduces privacy risks. The use of federated learning (FL) can alleviate this to some extent, but faces challenges of data heterogeneity, poor personalization, and expensive training data generation. We propose pFedRAG, a novel Personalized Federated RAG framework, which enables efficient collaborative fine-tuning of embedding models to address these challenges. The key contribution is a new Depth-Adaptive Tiered Embedding (DATE) architecture, which comprises a Global Shared Layer, combined using FL to capture common knowledge, and a Personalized Layer with adjustable depth tailored for local data and training results of each client. The depth is locally controlled based on crafted metrics and scoring criteria. Also, pFedRAG incorporates a fully client-side pipeline leveraging local small LLMs and vector database filtering to construct high-quality query-document pairs. Experiments on diverse medical non-IID document datasets demonstrate that pFedRAG significantly reduces communication costs, handles data heterogeneity, and improves retrieval performance. Human evaluations confirm the enhanced response quality of pFedRAG."
}