Skip to main content

ORIGINAL RESEARCH article

Front. Artif. Intell.
Sec. Natural Language Processing
Volume 7 - 2024 | doi: 10.3389/frai.2024.1404940
This article is part of the Research Topic Conversational Natural Language Interfaces (CNLIs) View all articles

Enhancing Educational Q&A Systems using a Chaotic Fuzzy Logic-Augmented Large Language Model

Provisionally accepted
Haoyuan Chen Haoyuan Chen 1Nuobei Shi Nuobei Shi 1Ling Chen Ling Chen 2Raymond Lee Raymond Lee 1*
  • 1 Beijing Normal University-Hong Kong Baptist University United International College, Zhuhai, Guangdong Province, China
  • 2 Beijing Institute of Technology, Zhuhai, Zhuhai, Guangdong Province, China

The final, formatted version of the article will be published soon.

    Online question-and-answer (Q&A) platforms are frequently replete with extensive human resources support. This paper proposes a novel methodology of a customized Large Language Model (LLM) called Chaotic LLMs-based Educational Q&A System (CHAQS) to navigate the complexities associated with intelligent Q&A systems for educational sector. It uses an expansive dataset comprising over 383,000 educational data pairs, an intricated 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 baseline model. Also, Fuzzy Logic is implemented to regulate parameters, system's adaptability with Lee Oscillator to refine model's response variability and precision. Experiment results showed that 5.12% improvement in Precision score, 11% increase in Recall metric, and 8%improvement in F1 score as compared to other models.

    Keywords: Education, Large Language Model, Lee-oscillator, Fuzzy Logic, AI-based QA System

    Received: 21 Mar 2024; Accepted: 23 Jul 2024.

    Copyright: © 2024 Chen, Shi, Chen and Lee. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Raymond Lee, Beijing Normal University-Hong Kong Baptist University United International College, Zhuhai, Guangdong Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.