@inproceedings{touayouch-etal-2026-divmerge,
    title = "{D}iv{M}erge: A divergence-based model merging method for multi-tasking",
    author = {Touayouch, Brahim  and
      Fosse, Lo{\"i}c  and
      Damnati, G{\'e}raldine  and
      Lecorv{\'e}, Gw{\'e}nol{\'e}},
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.337/",
    pages = "7157--7180",
    ISBN = "979-8-89176-380-7",
    abstract = "Merging fine-tuned models is a promising alternative to costly multi-task training, but task interference remains a challenge, especially as the number of tasks grows. We present DivMerge, a reference-free method that merges models trained on different tasks by minimizing Jensen-Shannon divergence between their outputs and those of the merged model, automatically balancing task importance. While the method exhibits strong theoretical properties, experiments on classification and generative tasks with autoregressive models show that DivMerge consistently outperforms prior work, and remains robust when scaling to more tasks."
}