SSU mitigates catastrophic forgetting in low-resource LLM target-language adaptation by scoring and column-wise freezing source-critical parameters, reducing source degradation to ~3% versus ~20% for full fine-tuning while matching target performance.
Cendol: Open instruction-tuned generative large language models for I ndonesian languages
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
Lius improves LLM translation for Kupang Malay by 4-13 points over baselines via continual instruction tuning with dictionary-derived instructions.
citing papers explorer
-
Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
SSU mitigates catastrophic forgetting in low-resource LLM target-language adaptation by scoring and column-wise freezing source-critical parameters, reducing source degradation to ~3% versus ~20% for full fine-tuning while matching target performance.
-
Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay
Lius improves LLM translation for Kupang Malay by 4-13 points over baselines via continual instruction tuning with dictionary-derived instructions.