@inproceedings{long-etal-2026-grouprank,
    title = "{G}roup{R}ank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with {LLM}s",
    author = "Long, Meixiu  and
      Sun, Duolin  and
      Yang, Dan  and
      Jiao, Yihan  and
      Liu, Lei  and
      Wang, Jiahai  and
      Hu, Binbin  and
      Shen, Yue  and
      Feng, Jie  and
      Tan, Zhehao  and
      Wang, Junjie  and
      Zhong, Lianzhen  and
      Wang, Jian  and
      Wei, Peng  and
      Gu, Jinjie",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1260/",
    pages = "25165--25186",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) have emerged as powerful tools for passage reranking in information retrieval, leveraging their superior reasoning capabilities to address the limitations of conventional models on complex queries. However, current LLM-based reranking paradigms are fundamentally constrained by an efficiency-accuracy trade-off: (1) pointwise methods are efficient but ignore inter-document comparison, yielding suboptimal accuracy; (2) listwise methods capture global context but suffer from context-window constraints and prohibitive inference latency. To address these issues, we propose GroupRank, a novel paradigm that balances flexibility and context awareness. To unlock the full potential of groupwise reranking, we propose an answer-free data synthesis pipeline that fuses local pointwise signals with global listwise rankings. These samples facilitate supervised fine-tuning and reinforcement learning, with the latter guided by a specialized \textit{group-ranking reward} comprising ranking-utility and group-alignment. These complementary components synergistically optimize document ordering and score calibration to reflect intrinsic query-document relevance.Experimental results show GroupRank achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED, while delivering a 6.4$\times$ inference speedup. The code is available at https://github.com/AQ-MedAI/Diver/tree/main/Reranker/GroupRank."
}