@inproceedings{hao-etal-2025-dynamic,
    title = "Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units",
    author = "Hao, Chao  and
      Wang, Zezheng  and
      Huang, Yanhua  and
      Xu, Ruiwen  and
      Niu, Wenzhe  and
      Liu, Xin  and
      Yu, Zitong",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.651/",
    pages = "12905--12922",
    ISBN = "979-8-89176-332-6",
    abstract = "This paper investigates the enhancement of reasoning capabilities in language models through token-level multi-model collaboration. Our approach selects the optimal tokens from the next token distributions provided by multiple models to perform autoregressive reasoning. Contrary to the assumption that more models yield better results, we introduce a distribution distance-based dynamic selection strategy (DDS) to optimize the multi-model collaboration process. To address the critical challenge of vocabulary misalignment in multi-model collaboration, we propose the concept of minimal complete semantic units (MCSU), which is simple yet enables multiple language models to achieve natural alignment within the linguistic space. Experimental results across various benchmarks demonstrate the superiority of our method. The codes will be released soon."
}