@inproceedings{liu-etal-2026-bcl,
    title = "{BCL}: {B}ayesian In-Context Learning Framework for Information Extraction",
    author = "Liu, Haoliang  and
      Cai, Chengkun  and
      Zhao, Xu  and
      Zhu, Han  and
      Huang, Shizhou  and
      Zhang, Xinglin  and
      Chen, Tao  and
      Hwang, Jenq-Neng  and
      Huaping, Zhang  and
      Li, Lei",
    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.1560/",
    pages = "31172--31189",
    ISBN = "979-8-89176-395-1",
    abstract = "Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability. Building on this, we propose BCL-IE (Bayesian In-Context Learning Framework for Information Extraction), the first optimization framework that uses particle filtering with Bayesian updates to systematically refine label representations across IE tasks. Through four steps{---}initialization, observation, weight update, and resampling, BCL-IE generalizes to both sequence labeling and relation classification paradigms. Extensive experiments demonstrate substantial improvements over existing approaches (up to 30{\%}), achieving prior performance while other methods either fail to generalize or show limited effectiveness."
}