[1B3-GS-2] Machine learning: Generative model

[1B3-GS-2-03] Ability to understand the logical structure of Large Language Models and generate predictive model

〇Toma Tanaka¹, Naofumi Emoto¹, Yumibayashi Tsukasa¹ (1. BrainPad Inc.)

Keywords:LLM, Supervised Learning, Meta Learning

The objective of this research is to understand the Ability to Understand the Logical Structure (AULS) in Large Language Models (LLMs).In this paper, we first introduce a method inspired by In-Context Learning (ICL), named "Inductive Bias Learning (IBL): Data2Code Model." We then apply IBL to several models, including GPT-4-Turbo, GPT-3.5-Turbo, and Gemini Pro, which have not been previously addressed in research, to compare and analyze the accuracy and characteristics of the predictive models they generate.The results demonstrated that all models possess the capability for IBL, with GPT-4-Turbo, in particular, achieving a notable improvement in accuracy compared to the conventional GPT-4. Furthermore, it was revealed that there is a variance in the performance of the predictive models generated between GPT-N and Gemini Pro.