Enhancing educational Q&A systems using a Chaotic Fuzzy Logic-Augmented large language model

Abstract

Introduction: Online question-and-answer (Q&A) platforms are frequently replete with extensive human resource support. This study proposes a novel methodology of a customized large language model (LLM) called Chaotic LLM-based Educational Q&A System (CHAQS) to navigate the complexities associated with intelligent Q&A systems for the educational sector. Methods: It uses an expansive dataset comprising over 383,000 educational data pairs, an intricate fine-tuning process encompassing p-tuning v2, low-rank adaptation (LRA), and strategies for parameter freezing at an open-source large language model ChatGLM as a baseline model. In addition, Fuzzy Logic is implemented to regulate parameters and the system's adaptability with the Lee Oscillator to refine the model's response variability and precision. Results: Experiment results showed a 5.12% improvement in precision score, an 11% increase in recall metric, and an 8% improvement in the F1 score as compared to other models. Discussion: These results suggest that the CHAQS methodology significantly enhances the performance of educational Q&A systems, demonstrating the effectiveness of combining advanced tuning techniques and fuzzy logic for improved model precision and adaptability.