A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search 事件

A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search arXiv:2602.11171v2 Announce Type: replace Abstract: Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) offers a resource-efficient way to personalize or specialize. However, LoRA is highly sensitive to hyperparameter choices, and exhaustive hyperparameter search is computationally expensive. To address this, we propose a Bayesian Optimization (BO) framework that leverages the domain knowledge