@inproceedings{hu-etal-2025-exploring,
    title = "Exploring Model Kinship for Merging Large Language Models",
    author = "Hu, Yedi  and
      Yao, Yunzhi  and
      Zhang, Ningyu  and
      Chen, Huajun  and
      Deng, Shumin",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-luhme/2025.findings-emnlp.32/",
    doi = "10.18653/v1/2025.findings-emnlp.32",
    pages = "596--625",
    ISBN = "979-8-89176-335-7",
    abstract = "Model merging has become one of the key technologies for enhancing the capabilities and efficiency of Large Language Models (LLMs). The open-source community has driven model evolution by iteratively merging existing models. However, a principled understanding of the expected gains and underlying factors in model merging remains lacking. In this work, we examine model evolution through continual merging, analogous to biological evolution, and introduce the concept of model kinship, the degree of similarity or relatedness between LLMs. With comprehensive empirical analysis, we find that there is a certain relationship between model kinship and the performance gains after model merging, which can help guide our selection of candidate models. Inspired by this, we propose a new model merging strategy: Top-$k$ Greedy Merging with Model Kinship, which can yield better performance on benchmark datasets. Specifically, we discover that using model kinship as a criterion can assist us in continuously performing model merging, alleviating the degradation (local optima) in model evolution, whereas model kinship can serve as a guide to escape these traps."
}