Related papers: LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks

URL: http://arxiv.org/abs/2402.11455v1
Date: Sun, 18 Feb 2024 04:41:25 GMT
Title: LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Authors: Hanqing Wang, Bowen Ping, Shuo Wang, Xu Han, Yun Chen, Zhiyuan Liu, Maosong Sun
Abstract summary: LoRA employs lightweight modules to customize large language models (LLMs) for each downstream task or domain. We propose LoRA-Flow, which utilizes dynamic weights to adjust the impact of different LoRAs. Experiments across six generative tasks demonstrate that our method consistently outperforms baselines with task-level fusion weights.
Score: 72.88244322513039
License: http://creativecommons.org/licenses/by/4.0/
Abstract: LoRA employs lightweight modules to customize large language models (LLMs) for each downstream task or domain, where different learned additional modules represent diverse skills. Combining existing LoRAs to address new tasks can enhance the reusability of learned LoRAs, particularly beneficial for tasks with limited annotated data. Most prior works on LoRA combination primarily rely on task-level weights for each involved LoRA, making different examples and tokens share the same LoRA weights. However, in generative tasks, different tokens may necessitate diverse skills to manage. Taking the Chinese math task as an example, understanding the problem description may depend more on the Chinese LoRA, while the calculation part may rely more on the math LoRA. To this end, we propose LoRA-Flow, which utilizes dynamic weights to adjust the impact of different LoRAs. The weights at each step are determined by a fusion gate with extremely few parameters, which can be learned with only 200 training examples. Experiments across six generative tasks demonstrate that our method consistently outperforms baselines with task-level fusion weights. This underscores the necessity of introducing dynamic fusion weights for LoRA combination.