@inproceedings{sajid-etal-2025-shot,
    title = "Few-Shot Multilingual Coreference Resolution Using Long-Context Large Language Models",
    author = "Sajid, Moiz  and
      Fraz, Muhammad  and
      Latif, Seemab  and
      Zafar, Zuhair",
    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/author-page-yu-wang-polytechnic/2025.crac-1.14/",
    doi = "10.18653/v1/2025.crac-1.14",
    pages = "154--162",
    abstract = "In this work, we present our system, which ranked second in the CRAC 2025 Shared Task on Multilingual Coreference Resolution (LLM Track). For multilingual coreference resolution, our system mainly uses long-context large language models (LLMs) in a few-shot in-context learning setting. Among the various approaches we explored, few-shot prompting proved to be the most effective, particularly due to the complexity of the task and the availability of high-quality data with referential relationships provided as part of the competition. We employed Gemini 2.5 Pro, one of the best available closed-source long-context LLMs at the time of submission. Our system achieved a CoNLL F1 score of 61.74 on the mini-testset, demonstrating that performance improves significantly with the number of few-shot examples provided, thanks to the model{'}s extended context window. While this approach comes with trade-offs in terms of inference cost and response latency, it highlights the potential of long-context LLMs for tackling multilingual coreference without task-specific fine-tuning. Although direct comparisons with traditional supervised systems are not straightforward, our findings provide valuable insights and open avenues for future work, particularly in expanding support for low-resource languages."
}