@inproceedings{li-etal-2025-coevo,
    title = "{C}o{E}vo: Coevolution of {LLM} and Retrieval Model for Domain-Specific Information Retrieval",
    author = "Li, Ang  and
      Wu, Yiquan  and
      Hu, Yinghao  and
      Qing, Lizhi  and
      Wang, Shihang  and
      Liu, Chengyuan  and
      Wu, Tao  and
      Jatowt, Adam  and
      Cai, Ming  and
      Wu, Fei  and
      Kuang, Kun",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.757/",
    pages = "14991--15010",
    ISBN = "979-8-89176-332-6",
    abstract = "Information retrieval in specialized domains (e.g., legal and medical) faces challenges in aligning user queries, often expressed in colloquial language, with highly structured, terminology-rich documents. This discrepancy creates a distribution gap in the text representation. Recent methods aim to enhance queries by generating intermediary elements (e.g., keywords, pseudo-documents) before performing retrieval with large language models (LLMs). However, by treating LLMs and retrievers separately, these approaches risk producing unreliable or irrelevant intermediaries, which can significantly degrade retrieval performance. To address this issue, we propose CoEvo, an alternating optimization framework that facilitates the coevolution of LLMs and retrieval models. CoEvo operates through two key steps: L-step directs the LLM in generating intermediaries by leveraging an archive of historical examples known to enhance retrieval. R-step trains the retriever using contrastive learning on the intermediaries produced by the LLM. Finally, we evaluate and flexibly leverage content generated by the LLM to amplify the effectiveness of coevolution. Experimental results demonstrate significant improvements in retrieval performance across both legal and medical domains."
}