BoRA: Bayesian Hierarchical Low-Rank Adaption for Multi-Task Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910774841049088 |
|---|---|
| author | Eide, Simen Frigessi, Arnoldo |
| author_facet | Eide, Simen Frigessi, Arnoldo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15857 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BoRA: Bayesian Hierarchical Low-Rank Adaption for Multi-Task Large Language Models Eide, Simen Frigessi, Arnoldo Machine Learning Computation and Language 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. |
| title | BoRA: Bayesian Hierarchical Low-Rank Adaption for Multi-Task Large Language Models |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2407.15857 |