@inproceedings{luo-etal-2026-imcoref,
    title = "{I}m{C}oref-{C}e{S}: An Improved Lightweight Pipeline for Coreference Resolution with {LLM}-based Checker-Splitter Refinement",
    author = "Luo, Kangyang  and
      Bai, Yuzhuo  and
      Si, Shuzheng  and
      Gao, Cheng  and
      Wang, Zhitong  and
      Shen, Yingli  and
      Li, Wenhao  and
      Liu, Zhu  and
      Han, Yufeng  and
      Wu, Jiayi  and
      Kong, Cunliang  and
      Sun, Maosong",
    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.1122/",
    pages = "24443--24471",
    ISBN = "979-8-89176-390-6",
    abstract = "Coreference Resolution (CR) is a critical task in Natural Language Processing (NLP). Current research faces a key dilemma: whether to further explore the potential of supervised neural methods based on small language models, whose detect-then-cluster pipeline still delivers top performance, or embrace the powerful capabilities of Large Language Models (LLMs). However, effectively combining their strengths remains underexplored. To this end, we propose \textbf{ImCoref-CeS}, a novel framework that integrates an enhanced supervised model with LLM-based reasoning. First, we present an improved CR method (\textbf{ImCoref}) to push the performance boundaries of the supervised neural method by introducing a lightweight bridging module to enhance long-text encoding capability, devising a biaffine scorer to comprehensively capture positional information, and invoking a hybrid mention regularization to improve training efficiency. Importantly, we employ an LLM acting as a multi-role Checker-Splitter agent to validate candidate mentions (filtering out invalid ones) and coreference results (splitting erroneous clusters) predicted by ImCoref. Extensive experiments demonstrate the effectiveness of ImCoref-CeS, which achieves superior performance compared to existing state-of-the-art (SOTA) methods."
}