Fine-Tuning Optimization of Small Language Models: A Novel Graph-Theoretical Approach for Efficient Prompt Engineering

Publication Date

1-1-2024

Document Type

Conference Proceeding

Publication Title

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB

DOI

10.1109/BMSB62888.2024.10608341

Abstract

In the realm of fine-tuning pre-trained language models in modern prompt engineering, we introduce a novel graph-theoretical approach to address the resource-intensive challenges to the conventional data fine-tuning methods for prompt engineering. Leveraging semantic and contextual prompt relationships, we propose to form a novel prompt graph, which facilitates a new comprehensive representation of prompt similarities. Building upon this new graph structure, our proposed approach can minimize the training time during the fine-tuning process for small language models by identifying and utilizing cliques corresponding to condensed subsets of highly similar prompts. This new strategic reduction in training data can greatly reduce the training time, particularly for resource-constrained applications in practice. Our proposed new approach leads to a significant reduction in the original prompt-graph order and a more focused and streamlined fine-tuning process. This data-reduction strategy demonstrates the potential to enable finetuning language models for prompt engineering with smaller datasets subject to less computational resource. The real run-time analysis for the training process of a small language model GPT2 have been undertaken to show the advantage of our proposed new approach.

Keywords

Artificial intelligence (AI) driven prompt engineering, clique, computational complexity, fine-tuning, graph, pre-trained language models, prompt engineering, small language models (SLMs), training data reduction (TDR)

Department

Applied Data Science

Link to Full Text

Share

COinS