L-TUNING: SYNCHRONIZED LABEL TUNING FOR PROMPT AND PREFIX IN LLMS

Published: 19 Mar 2024, Last Modified: 14 Aug 2024Tiny Papers @ ICLR 2024 PresentEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Prompt tuning, Prefix tuning, Transformer, Large language model, Natural language inference
TL;DR: L-Tuning introduces an efficient prompt/prefix tuning approach that enhances LLMs for classification by leveraging pre-trained semantics for distinct label embeddings
Abstract: 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: https://github.com/Kowsher/L-Tuning
Submission Number: 50
Loading