LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild

Ziyu Zhao, Leilei Gan, Guoyin Wang, Wangchunshu Zhou, Hongxia Yang, Kun Kuang, Fei Wu


Abstract
Low-Rank Adaptation (LoRA) provides an effective yet efficient solution for fine-tuning large language models (LLMs). The modular and plug-and-play nature of LoRA enables the integration of diverse domain-specific LoRAs to enhance the capabilities of LLMs. Previous research on exploiting multiple LoRAs either focuses on specific isolated downstream tasks or fixes the selection of LoRAs during training. However, in real-world scenarios, LLMs receive diverse prompts covering different tasks, and the pool of candidate LoRAs is often dynamically updated. To bridge this gap, we propose LoraRetriever, a retrieve-then-compose framework that adaptively retrieves and composes multiple LoRAs according to the input prompts. LoraRetriever contains three main components: firstly, identifying and retrieving LoRAs relevant to the given input; secondly, formulating strategies for effectively integrating the retrieved LoRAs; and thirdly, developing efficient batch inference to accommodate heterogeneous requests. Experimental results indicate that LoraRetriever consistently outperforms the baselines, highlighting its practical effectiveness and versatility. Our code is available at https://github.com/StyxXuan/LoraRetriever.
Anthology ID:
2024.findings-acl.263
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4447–4462
Language:
URL:
https://aclanthology.org/2024.findings-acl.263
DOI:
10.18653/v1/2024.findings-acl.263
Bibkey:
Cite (ACL):
Ziyu Zhao, Leilei Gan, Guoyin Wang, Wangchunshu Zhou, Hongxia Yang, Kun Kuang, and Fei Wu. 2024. LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild. In Findings of the Association for Computational Linguistics ACL 2024, pages 4447–4462, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild (Zhao et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.findings-acl.263.pdf