Challenge Track: Breaking Language Barriers: Adapting NLLB-200 and mBART for Bhilli, Gondi, Mundari, and Santali Without Source Language Proficiency

Paul Kamau

Keywords: Low-Resource NMT, Cross-Lingual Transfer, NLLB, mBART, Ensemble Learning, Data-Centric AI, Indic Languages

TL;DR: A top-5 solution for MMLoSo 2025 demonstrating that fine-tuning massive multilingual models with heuristic-based conservative ensembling effectively translates low-resource Indian languages without native speaker proficiency

Abstract: This paper presents a language-agnostic approach to neural machine translation for low-resource Indian tribal languages: Bhilli, Gondi, Mundari, and Santali. Developed under the constraint of zero proficiency in the source languages, the methodology relies on the cross-lingual transfer capabilities of two foundation models, NLLB-200 and mBART-50. The approach employs a unified bidirectional fine-tuning strategy to maximize limited parallel corpora. A primary contribution of this work is a smart post-processing pipeline and a "conservative ensemble" mechanism. This mechanism integrates predictions from a secondary model specifically as a safety net to mitigate hallucinations and length-ratio artifacts generated by the primary model. The approach achieved a private leaderboard score of 179.49 in the MMLoSo 2025 Language Challenge. These findings demonstrate that effective translation systems for underrepresented languages can be engineered without native linguistic intuition by leveraging data-centric validation and the latent knowledge within massive multilingual models

Submission Number: 23