JSAI2024

Presentation information

General Session

General Session » GS-2 Machine learning

[2D1-GS-2] Machine learning: Evolutionary computation / Network

Wed. May 29, 2024 9:00 AM - 10:40 AM Room D (Temporary room 2)

座長:高野 諒(富山県立大学 情報工学部 データサイエンス学科)

9:40 AM - 10:00 AM

[2D1-GS-2-03] Learning Large Language Models for Code Generation through Genetic Algorithms and Knowledge Distillation

〇Takashi Miwa1, Shin-Nosuke Ishikawa1 (1. Graduate School of Artificial Intelligence and Science, RIKKYO UNIVERSITY)

Keywords:Genetic Algorithm, Knowledge Distillation, Hyperparameter Optimization, LLM for Code Generation, AutoML

Drawing inspiration from open-ended evolution, this paper explores the concept of individual Large Language Models (LLMs) functioning as autonomous agents while advancing learning as a group, aiming to solve complex problems that are challenging for a single model. As a specific method, we propose a learning process that combines genetic algorithms with knowledge distillation. By progressing learning through knowledge distillation and simultaneously optimizing hyperparameters with genetic algorithms, we aim for more efficient learning. For the domain task, we selected the code generation task of producing Python code from instructions. In our experiments, we utilized three student models and one teacher model for learning. The results showed a 1.2% improvement in accuracy on HumanEval’s pass@1, indicating signs of optimized learning rates as learning progressed. However, challenges remain in achieving significant accuracy improvements and optimizing a variety of hyperparameters.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password