2 papers
cs.CL2025
FISH-Tuning: Enhancing PEFT Methods with Fisher Information
Kang Xue, Ming Dong, Xinhui Tu +1
The rapid growth in the parameter size of Large Language Models (LLMs) has spurred the development of Parameter-Efficient Fine-Tuning (PEFT) methods to mitigate the substantial com…
cs.CL2024
Targeted Efficient Fine-tuning: Optimizing Parameter Updates with Data-Driven Sample Selection
Ming Dong, Kang Xue, Bolong Zheng +1
Fine-tuning all parameters of Large Language Models (LLMs) is computationally expensive. Parameter-Efficient Fine-Tuning (PEFT) methods address this by selectively fine-tuning spec…