Skip to yearly menu bar Skip to main content

Workshop: Socially Responsible Language Modelling Research (SoLaR)

Bayesian low-rank adaptation for large language models

Adam Yang · Maxime Robeyns · Xi Wang · Laurence Aitchison


Low-rank adaptation (LoRA) has emerged as a new paradigm for cost-efficient fine-tuning of large language models (LLMs). 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, which applies a Bayesian approach to the LoRA parameters. Specifically, Laplace-LoRA applies a Laplace approximation to the posterior over the LoRA parameters, considerably improving the calibration of fine-tuned LLMs.

Chat is not available.