Bayesian Low-rank Adaptation for Large Language Models

Adam X. Yang; Maxime Robeyns; Xi Wang; Laurence Aitchison

ICLR 2024poster75 citations

Bayesian Low-rank Adaptation for Large Language Models

Adam X. Yang, Maxime Robeyns, Xi Wang, Laurence Aitchison

Abstract

Parameter-efficient fine-tuning (PEFT) has emerged as a new paradigm for cost-efficient fine-tuning of large language models (LLMs), with low-rank adaptation (LoRA) being a widely adopted choice. However, fine-tuned LLMs often become overconfident especially when fine-tuned on small datasets. Bayesian methods, with their inherent ability to estimate uncertainty, serve as potent tools to mitigate overconfidence and enhance calibration. In this work, we introduce Laplace-LoRA, a straightforward yet effective Bayesian method, which applies the Laplace approximation to the LoRA parameters and, considerably boosts the calibration of fine-tuned LLMs.

Large language modelsBayesian deep learningLaplace approximationuncertainty calibration

BibTeX

@inproceedings{
yang2024bayesian,
title={Bayesian Low-rank Adaptation for Large Language Models},
author={Adam X. Yang and Maxime Robeyns and Xi Wang and Laurence Aitchison},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=FJiUyzOF1m}
}