@inproceedings{mo-etal-2025-uniconv,
    title = "{U}ni{C}onv: Unifying Retrieval and Response Generation for Large Language Models in Conversations",
    author = "Mo, Fengran  and
      Gao, Yifan  and
      Meng, Chuan  and
      Liu, Xin  and
      Wu, Zhuofeng  and
      Mao, Kelong  and
      Wang, Zhengyang  and
      Chen, Pei  and
      Li, Zheng  and
      Li, Xian  and
      Yin, Bing  and
      Jiang, Meng",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.344/",
    pages = "6936--6949",
    ISBN = "979-8-89176-251-0",
    abstract = "The rapid advancement of conversational search systems revolutionizes how information is accessed by enabling the multi-turn interaction between the user and the system. Existing conversational search systems are usually built with two different models. This separation restricts the system from leveraging the intrinsic knowledge of the models simultaneously, which cannot ensure the effectiveness of retrieval benefiting the generation. The existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses. In this paper, we explore how to unify dense retrieval and response generation for large language models in conversation. We conduct joint fine-tuning with different objectives and design two mechanisms to reduce the inconsistency risks while mitigating data discrepancy. The evaluations on five conversational search datasets demonstrate that our unified model can mutually improve both tasks and outperform the existing baselines."
}