Large language models excel in English but still struggle with complex reasoning in many low-resource languages (LRLs). Existing encoder-plus-decoder methods such as LangBridge and MindMerger raise accuracy on mid and high-resource languages, yet they leave a large gap on LRLs. We present MERLIN, a two-stage model-stacking framework that applies a curriculum learning strategy -- from general bilingual bitext to 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. It also yields consistent gains on MGSM and MSVAMP (+0.9 and +2.8 pp), demonstrating effectiveness across both low and high-resource settings.
@article{arxiv.2509.08105,
title = {MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder-LLM Integration in Cross-Lingual Reasoning},
author = {Kosei Uemura and David Guzmán and Quang Phuoc Nguyen and Jesujoba Oluwadara Alabi and En-shiun Annie Lee and David Ifeoluwa Adelani},
journal= {arXiv preprint arXiv:2509.08105},
year = {2026}
}