@inproceedings{phuc-thin-2025-shot,
    title = "Few-Shot Coreference Resolution with Semantic Difficulty Metrics and In-Context Learning",
    author = "Phuc, Nguyen Xuan  and
      Thin, Dang Van",
    editor = "Ogrodniczuk, Maciej  and
      Novak, Michal  and
      Poesio, Massimo  and
      Pradhan, Sameer  and
      Ng, Vincent",
    booktitle = "Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.crac-1.13/",
    doi = "10.18653/v1/2025.crac-1.13",
    pages = "149--153",
    abstract = "This paper presents our submission to the CRAC 2025 Shared Task on Multilingual Coreference Resolution in the LLM track. We propose a prompt-based few-shot coreference resolution system where the final inference is performed by Grok-3 using in-context learning. The core of our methodology is a difficulty- aware sample selection pipeline that leverages Gemini Flash 2.0 to compute semantic diffi- culty metrics, including mention dissimilarity and pronoun ambiguity. By identifying and selecting the most challenging training sam- ples for each language, we construct highly informative prompts to guide Grok-3 in predict- ing coreference chains and reconstructing zero anaphora. Our approach secured 3rd place in the CRAC 2025 shared task."
}