@article{ART003074067},
author={Lib Kim and Namgyu Kim},
title={Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2024},
volume={29},
number={4},
pages={9-21},
doi={10.9708/jksci.2024.29.04.009}
TY - JOUR
AU - Lib Kim
AU - Namgyu Kim
TI - Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning
JO - Journal of The Korea Society of Computer and Information
PY - 2024
VL - 29
IS - 4
PB - The Korean Society Of Computer And Information
SP - 9
EP - 21
SN - 1598-849X
AB - Deep learning has been developing rapidly in recent years, with many researchers working to utilize large language models in various domains. However, there are practical difficulties that developing and utilizing language models require massive data and high-performance computing resources. Therefore, in-context learning, which utilizes prompts to learn efficiently, has been introduced, but there needs to be clear criteria for effective prompts for learning. In this study, we propose a methodology for enhancing prompt-based learning performance by improving the PET technique, which is one of the contextual learning methods, to select PVPs that are similar to the context of existing data. To evaluate the performance of the proposed methodology, we conducted experiments with 30,100 restaurant review datasets collected from Yelp, an online business review platform. We found that the proposed methodology outperforms traditional PET in all aspects of accuracy, stability, and learning efficiency.
KW - Pre-trained language model;Large language model;In-context learning;Prompt-based learning;PET
DO - 10.9708/jksci.2024.29.04.009
ER -
Lib Kim and Namgyu Kim. (2024). Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning. Journal of The Korea Society of Computer and Information, 29(4), 9-21.
Lib Kim and Namgyu Kim. 2024, "Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning", Journal of The Korea Society of Computer and Information, vol.29, no.4 pp.9-21. Available from: doi:10.9708/jksci.2024.29.04.009
Lib Kim, Namgyu Kim "Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning" Journal of The Korea Society of Computer and Information 29.4 pp.9-21 (2024) : 9.
Lib Kim, Namgyu Kim. Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning. 2024; 29(4), 9-21. Available from: doi:10.9708/jksci.2024.29.04.009
Lib Kim and Namgyu Kim. "Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning" Journal of The Korea Society of Computer and Information 29, no.4 (2024) : 9-21.doi: 10.9708/jksci.2024.29.04.009
Lib Kim; Namgyu Kim. Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning. Journal of The Korea Society of Computer and Information, 29(4), 9-21. doi: 10.9708/jksci.2024.29.04.009
Lib Kim; Namgyu Kim. Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning. Journal of The Korea Society of Computer and Information. 2024; 29(4) 9-21. doi: 10.9708/jksci.2024.29.04.009
Lib Kim, Namgyu Kim. Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning. 2024; 29(4), 9-21. Available from: doi:10.9708/jksci.2024.29.04.009
Lib Kim and Namgyu Kim. "Context-Based Prompt Selection Methodology to Enhance Performance in Prompt-Based Learning" Journal of The Korea Society of Computer and Information 29, no.4 (2024) : 9-21.doi: 10.9708/jksci.2024.29.04.009
