2025-01-12-eide25a.md

title	openreview	software	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
BoRA: Bayesian Hierarchical Low-Rank Adaption for Multi-task Large Language Models	bkQRCWYrMb	https://github.com/simeneide/bora	This paper introduces Bayesian Hierarchical Low-Rank Adaption (BoRA), a novel method for finetuning multi-task Large Language Models (LLMs). Current finetuning approaches, such as Low-Rank Adaption (LoRA), perform exeptionally well in reducing training parameters and memory usage but face limitations when applied to multiple similar tasks. Practitioners usually have to choose between training separate models for each task or a single model for all tasks, both of which come with trade-offs in specialization and data utilization. BoRA addresses these trade-offs by leveraging a Bayesian hierarchical model that allows tasks to share information through global hierarchical priors. This enables tasks with limited data to benefit from the overall structure derived from related tasks while allowing tasks with more data to specialize. Our experimental results show that BoRA outperforms both individual and unified model approaches, achieving lower perplexity and better generalization across tasks. This method provides a scalable and efficient solution for multi-task LLM finetuning, with significant practical implications for diverse applications.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	eide25a	0	Bo{RA}: Bayesian Hierarchical Low-Rank Adaption for Multi-task Large Language Models	51	57	51-57	51	false	Eide, Simen and Frigessi, Arnoldo	given family Simen Eide given family Arnoldo Frigessi	2025-01-12		Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL)	265	inproceedings	date-parts 2025 1 12	https://raw.githubusercontent.com/mlresearch/v265/main/assets/eide25a/eide25a.pdf