Rakhun Kim

Comparing LoRA, DoRA, and OFT for Extremely Low-Resource English–Sango Machine Translation: Adaptation Performance and Out-of-Domain Retention

Extremely low-resource machine translation poses a difficult cross-lingual adaptation problem: improving target-language performance while preserving capabilities acquired through multilingual pretraining. This study compares three mathematically distinct parameter-efficient fine-tuning (PEFT) methods—LoRA, DoRA, and o...