Analyzing the Taxonomy of Large Language Models using Logistic Regression

Abstract

Gathering and understanding the available survey papers with different categories is becoming more of a challenge with the rapid growth of the field of Large Language Models (LLMs). In this study, 144 survey papers are analyzed using a logistics regression classifier to predict the taxonomy category of the papers. According to the results, the logistic regression model accurately reflects the core trends within the collected data effectively and provides reasonable insight for the classification of the paper's taxonomy. This approach might be helpful for researchers to organize their studies in a growing field of large language models. The results of the study show that the logistic regression approach is a reliable approach for taxonomy classification.