Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models

arXiv:2405.03425v1 Announce Type: new
Abstract: Fine-tuned Large Language Models (LLMs) often suffer from overconfidence and poor calibration, particularly when fine-tuned on small datasets. To address these challenges, we propose a simple combination of Low-Rank Adaptation (LoRA) with Gaussian Stochastic Weight Averaging (SWAG), facilitating approximate Bayesian inference in LLMs. Through extensive testing across several Natural Language Processing (NLP) benchmarks, we demonstrate that our straightforward and computationally efficient approach improves model generalization and calibration. We further show that our method exhibits greater …

abstract arxiv bayesian bayesian inference calibration challenges combination cs.cl datasets inference language language models large language large language models llms lora low low-rank adaptation simple small stochastic type