@inproceedings{ye-etal-2025-q,
    title = "{Q}-{PRM}: Adaptive Query Rewriting for Retrieval-Augmented Generation via Step-level Process Supervision",
    author = "Ye, Xiaopeng  and
      Xu, Chen  and
      Zhang, Chaoliang  and
      Du, Zhaocheng  and
      Xu, Jun  and
      Wang, Gang  and
      Dong, Zhenhua",
    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/name-variant-enfa-fane/2025.findings-emnlp.817/",
    doi = "10.18653/v1/2025.findings-emnlp.817",
    pages = "15113--15128",
    ISBN = "979-8-89176-335-7",
    abstract = "Query rewriting plays a pivotal role in Retrieval-Augmented Generation (RAG) by refining real-world queries of varying complexity. Existing approaches typically rely on outcome-supervised training or heuristic rules to guide the rewriting process. However, these paradigms often struggle to handle queries with varying levels of complexity, posing over- and under-refinement problems. We identify the root cause of these issues as the absence of supervision signals for intermediate steps. To fully construct and utilize such signals, we propose Q-PRM, a novel query rewriting framework. Q-PRM reformulates the rewriting process as a Markov Decision Process (MDP) composed of atomic rewriting steps. In this way, Q-PRM can apply process-level supervision to each atomic step according to the query type, offering more targeted and effective guidance. Q-PRM comprises three key stages: (1) applying Monte Carlo Tree Search to generate step-level process supervision signals; (2) performing reinforced self-training for progressive process refinement; and (3) employing PRM-guided decoding during inference. Experiments on several open-domain QA benchmarks demonstrate that Q-PRM consistently outperforms baselines across different levels of query complexity."
}