@inproceedings{yang-etal-2026-dfams,
    title = "{DFAMS}: Dynamic-flow guided Federated Alignment based Multi-prototype Search",
    author = "Yang, Zhibang  and
      Jiang, Xinke  and
      Qiu, Rihong  and
      Li, Ruiqing  and
      Zhang, Yihang  and
      Fang, Yue  and
      Xu, Yongxin  and
      Ding, Hongxin  and
      Chu, Xu  and
      Zhao, Junfeng  and
      Wang, Yasha",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1135/",
    pages = "24728--24752",
    ISBN = "979-8-89176-390-6",
    abstract = "Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, existing methods struggle to retrieve high-quality and relevant documents for ambiguous queries, especially in cross-domain scenarios, which significantly limits their effectiveness in supporting downstream generation tasks. Inspired by Dynamic Information Flow (DIF), we propose DFAMS, a novel framework that leverages DIF to identify latent query intents and construct semantically aligned knowledge partitions for accurate retrieval across heterogeneous sources. Specifically, DFAMS probes the DIF in LLMs by leveraging gradient signals from a few annotated queries and employing Shapley value-based attribution to trace neuron activation paths associated with intent recognition and subdomain boundary detection. Then, DFAMS leverages DIF to train an alignment module via multi-prototype contrastive learning, enabling fine-grained intra-source modeling and inter-source semantic alignment across knowledge bases. Experimental results across five benchmarks show that DFAMS outperforms advanced FR methods by up to 14.37{\%} in knowledge classification accuracy, 5.38{\%} in retrieval recall, and 6.45{\%} in downstream QA accuracy, demonstrating its effectiveness in complex FR scenarios. Our code is publicly available at https://github.com/Artessay/DFAMS."
}