Bayesian Low-rank Adaptation for Large Language Models
This work addresses overconfidence issues in fine-tuned LLMs, particularly for applications requiring reliable uncertainty estimates, but it is incremental as it builds on existing LoRA methods.
The authors tackled the problem of overconfidence in fine-tuned large language models by introducing Laplace-LoRA, a Bayesian adaptation method that applies a Laplace approximation to LoRA parameters, resulting in improved calibration.
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.