Fine-tuning Gemma models on translated Marathi Alpaca with LoRA usually lowers automated benchmark scores, while a small manual evaluation points the other way, exposing evaluation gaps for low-resource languages.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Challenges in Adapting Multilingual LLMs to Low-Resource Languages using LoRA PEFT Tuning
Fine-tuning Gemma models on translated Marathi Alpaca with LoRA usually lowers automated benchmark scores, while a small manual evaluation points the other way, exposing evaluation gaps for low-resource languages.