@inproceedings{uemura-etal-2026-merlin,
    title = "{MERLIN}: Multi-Stage Curriculum Alignment for Multilingual Encoder-{LLM} Integration in Cross-Lingual Reasoning",
    author = "Uemura, Kosei  and
      Guzm{\'a}n, David  and
      Nguyen, Quang Phuoc  and
      Alabi, Jesujoba Oluwadara  and
      Lee, En-Shiun Annie  and
      Adelani, David Ifeoluwa",
    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.277/",
    pages = "5909--5924",
    ISBN = "979-8-89176-380-7",
    abstract = "Large language models (LLMs) excel in English but still struggle with complex reasoning in many low-resource languages (LRLs). Existing methods align LLMs with multilingual encoders, such as LangBridge and MindMerger, raising the accuracy for mid and high-resource languages, yet large performance gap remains for LRLs. We present MERLIN, a model-stacking framework that iteratively refines in 2-stages based on a curriculum strategy (from general to specific where general is bilingual bitext and specific is task-specific data) and adapts only a small set of DoRA weights. On the AfriMGSM benchmark MERLIN improves exact-match accuracy by +12.9 pp over MindMerger and outperforms GPT-4o-mini by 15.2 pp. It also yields consistent gains on MGSM and MSVAMP (+0.9 and +2.8 pp), demonstrating effectiveness across both low and high-resource settings."
}