@inproceedings{ostapenko2024towards,
author = {Ostapenko, O. and Su, Zhan and Ponti, E. and Charlin, Laurent and Le Roux, Nicolas and Pereira, Matheus and Caccia, Lucas and Sordoni, Alessandro},
title = {Towards Modular LLMs by Building and Reusing a Library of LoRAs},
booktitle = {ICML 2024},
year = {2024},
month = {May},
abstract = {The growing number of parameter-efficient adaptations of a base large language model (LLM) calls for studying whether we can reuse such trained adapters to improve performance for new tasks. We study how to best build a library of adapters given multi-task data and devise techniques for both zero-shot and supervised task generalization through routing in such library. We benchmark existing approaches to build this library and introduce model-based clustering, MBC, a method that groups tasks based on the similarity of their adapter parameters, indirectly optimizing for transfer across the multi-task dataset. To re-use the library, we present a novel zero-shot routing mechanism, Arrow, which enables dynamic selection of the most relevant adapters for new inputs without the need for retraining. We experiment with several LLMs, such as Phi-2 and Mistral, on a wide array of held-out tasks, verifying that MBC-based adapters and Arrow routing lead to superior generalization to new tasks. We make steps towards creating modular, adaptable LLMs that can match or outperform traditional joint training.},
url = {http://approjects.co.za/?big=en-us/research/publication/towards-modular-llms-by-building-and-reusing-a-library-of-loras/},
}