← all papers · overview

Bayesian-lora: Probabilistic Low-rank Adaptation Of Large Language Models

Abstract

Large Language Models usually put more emphasis on accuracy and therefore, will guess even when not certain about the prediction, which is especially severe when fine-tuned on small datasets due to the inherent tendency toward miscalibration. In this work, we introduce Bayesian-LoRA, which reformulates the deterministic LoRA update as a probabilistic low-rank representation inspired by Sparse Gaus

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).