GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection

ArXi:2603.09865v1 Announce Type: new Parameter-Efficient Fine-Tuning (PEFT) has become a key strategy for adapting large language models, with recent advances in sparse tuning reducing overhead by selectively updating key parameters or subsets of data. Existing approaches generally focus on two distinct paradigms: layer-selective methods aiming to fine-tune critical layers to minimize computational load, and data-selective methods aiming to select effective.