Efficiently fine-tuning Large Language Models (LLMs) for specific tasks
presents a considerable challenge in natural language processing. Traditional
methods, like prompt or prefix tuning, typically rely on arbitrary tokens for
training, leading to prolonged training times and generalized token use across
various class labels. To address these issues, this paper introduces L-Tuning,
an efficient fine-tuning approach designed for classification tasks within the
Natural Language Inference (NLI) framework. Diverging from conventional
methods, L-Tuning focuses on the fine-tuning of label tokens processed through
a pre-trained LLM, thereby harnessing its pre-existing semantic knowledge. This
technique not only improves the fine-tuning accuracy and efficiency but also
facilitates the generation of distinct label embeddings for each class,
enhancing the model's training nuance. Our experimental results indicate a
significant improvement in training efficiency and classification accuracy with
L-Tuning compared to traditional approaches, marking a promising advancement in
fine-tuning LLMs for complex language tasks. \\ Code is available at:
\textcolor{red}{\href{https://github.com/Kowsher/L-Tuning}{\texttt{this https URL}}}.

传统方法在对大型语言模型（LLMs）进行任务微调时面临着挑战。这篇论文介绍了一种名为 L-Tuning 的有效微调方法，专为自然语言推理（NLI）框架中的分类任务而设计，通过对预训练 LLM 进行标签令牌的微调，从而改善模型的训练效果和分类准确度，并提高训练效率。