@inproceedings{luo-etal-2026-meic,
    title = "{MEIC}-{DT}: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints",
    author = "Luo, Kangyang  and
      Si, Shuzheng  and
      Bai, Yuzhuo  and
      Gao, Cheng  and
      Wang, Zhitong  and
      Huang, Cheng  and
      Shen, Yingli  and
      Han, Yufeng  and
      Li, Wenhao  and
      Kong, Cunliang  and
      Sun, Maosong",
    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.881/",
    pages = "17787--17804",
    ISBN = "979-8-89176-395-1",
    abstract = "In the era of large language models (LLMs), supervised neural methods remain the state-of-the-art (SOTA) for Coreference Resolution. Yet, their full potential is underexplored, particularly in incremental clustering, which faces the critical challenge of balancing efficiency with performance for long texts. To address the limitation, we propose MEIC-DT, a novel dual-threshold, memory-efficient incremental clustering approach based on a lightweight Transformer. MEIC-DT features a dual-threshold constraint mechanism designed to precisely control the Transformer{'}s input scale within a predefined memory budget. This mechanism incorporates two key components: a Statistics-Aware Eviction Strategy (SAES) and an Internal Regularization Policy (IRP). The SAES utilizes distinct statistical profiles from the training and inference phases for intelligent cache management. The IRP strategically condenses clusters by selecting the most representative mentions, thereby preserving semantic integrity. Extensive experiments on common benchmarks demonstrate that MEIC-DT achieves highly competitive coreference performance under stringent memory constraints."
}