@inproceedings{daohuan-etal-2025-system,
    title = "System Report for {CCL}25-Eval Task 4: Prompting, Scheduling, and Arbitration Strategies for {C}hinese Factivity Inference",
    author = "Daohuan, Liu  and
      Lun, Xia  and
      Zhang, Yuxuan  and
      Yang, Xinyu  and
      Kong, Fanzhen",
    editor = "Lin, Hongfei  and
      Li, Bin  and
      Tan, Hongye",
    booktitle = "Proceedings of the 24th {C}hina National Conference on Computational Linguistics ({CCL} 2025)",
    month = aug,
    year = "2025",
    address = "Jinan, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/ingest-ccl/2025.ccl-2.17/",
    pages = "146--151",
    abstract = "This report presents the methodology and findings of prompting large language models (LLMs) for Chinese Factivity Inference (FI). We evaluated five LLMs, among which DeepSeek-R1 demonstrated the best overall performance. A combination of Chain-of-Thought (CoT), few-shot, and system-level instructions were combined for final prompting. Additionally, we introduced a pairwise task scheduling strategy and a multi-agent disagreement arbitration mechanism to further enhance inference quality. Experimental results show that the integration of prompting, scheduling, and arbitration strategies significantly improves performance, with DeepSeek-R1 achieving 91.7{\%} overall accuracy on the evaluation set. The report also highlights findings regarding LLM behavior on FI tasks and outlines potential directions for future improvement."
}