By sharing the B matrix across adapters instead of the A matrix, ALoRA and Fed-ALoRA deliver more balanced performance in multi-task and federated LLM fine-tuning.
Samo: A lightweight sharpness-aware approach for multi-task optimization with joint global-local perturbation.arXiv preprint arXiv:2507.07883
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs
By sharing the B matrix across adapters instead of the A matrix, ALoRA and Fed-ALoRA deliver more balanced performance in multi-task and federated LLM fine-tuning.