Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Personalizing Education through an Adaptive LMS with Integrated LLMs

Kyle Spriggs, Meng Cheng Lau, Kalpdrum Passi

TL;DR

This paper presents an adaptive learning management system (ALMS) that personalizes education by integrating multiple domain-specific and general-purpose LLMs within an LMS, addressing privacy, accuracy, and cost through retrieval-augmented generation (RAG) and vector embeddings. The authors implement a hybrid architecture combining an expert system with LLM-driven question answering, evaluate Phase II/III prototypes using a rigorous benchmarking framework across mathematics, reading, writing, reasoning, and coding, and compare self-hosted versus API-based models. Key findings show self-hosted LLMs can match or closely approach proprietary models in several domains, RAG reduces hallucinations, and a hybrid ES-LLM approach balances performance, privacy, and cost. The work highlights practical implications for privacy-preserving, scalable ALMS deployments and outlines concrete directions for future benchmarking, vector-store integration, and system prompts to optimize educational outcomes.

Abstract

The widespread adoption of large language models (LLMs) marks a transformative era in technology, especially within the educational sector. This paper explores the integration of LLMs within learning management systems (LMSs) to develop an adaptive learning management system (ALMS) personalized for individual learners across various educational stages. Traditional LMSs, while facilitating the distribution of educational materials, fall short in addressing the nuanced needs of diverse student populations, particularly in settings with limited instructor availability. Our proposed system leverages the flexibility of AI to provide a customizable learning environment that adjusts to each user's evolving needs. By integrating a suite of general-purpose and domain-specific LLMs, this system aims to minimize common issues such as factual inaccuracies and outdated information, characteristic of general LLMs like OpenAI's ChatGPT. This paper details the development of an ALMS that not only addresses privacy concerns and the limitations of existing educational tools but also enhances the learning experience by maintaining engagement through personalized educational content.

Personalizing Education through an Adaptive LMS with Integrated LLMs

TL;DR

This paper presents an adaptive learning management system (ALMS) that personalizes education by integrating multiple domain-specific and general-purpose LLMs within an LMS, addressing privacy, accuracy, and cost through retrieval-augmented generation (RAG) and vector embeddings. The authors implement a hybrid architecture combining an expert system with LLM-driven question answering, evaluate Phase II/III prototypes using a rigorous benchmarking framework across mathematics, reading, writing, reasoning, and coding, and compare self-hosted versus API-based models. Key findings show self-hosted LLMs can match or closely approach proprietary models in several domains, RAG reduces hallucinations, and a hybrid ES-LLM approach balances performance, privacy, and cost. The work highlights practical implications for privacy-preserving, scalable ALMS deployments and outlines concrete directions for future benchmarking, vector-store integration, and system prompts to optimize educational outcomes.

Abstract

The widespread adoption of large language models (LLMs) marks a transformative era in technology, especially within the educational sector. This paper explores the integration of LLMs within learning management systems (LMSs) to develop an adaptive learning management system (ALMS) personalized for individual learners across various educational stages. Traditional LMSs, while facilitating the distribution of educational materials, fall short in addressing the nuanced needs of diverse student populations, particularly in settings with limited instructor availability. Our proposed system leverages the flexibility of AI to provide a customizable learning environment that adjusts to each user's evolving needs. By integrating a suite of general-purpose and domain-specific LLMs, this system aims to minimize common issues such as factual inaccuracies and outdated information, characteristic of general LLMs like OpenAI's ChatGPT. This paper details the development of an ALMS that not only addresses privacy concerns and the limitations of existing educational tools but also enhances the learning experience by maintaining engagement through personalized educational content.

Paper Structure

This paper contains 29 sections, 18 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Artificial Intelligence in Education
  4. Expert Systems
  5. Large Language Models
  6. Methodology
  7. Implementation
  8. Expert System
  9. LLM Question-Answering Machine
  10. Experimental Design
  11. Benchmarking System Design
  12. Mathematics Test Design
  13. Reading Test Design
  14. Writing Test Design
  15. Reasoning Test Design
  16. ...and 14 more sections

Figures (18)

  • Figure 1: Screen capture of user interface. A: Query input, B: ContentPanel-1 (closest match), C: ContentPanel-2, D: ContentPanel-3, E: ContentPanel-4.
  • Figure 2: Backend DFD
  • Figure 3: Frontend state diagram
  • Figure 4: Mean score across all LLMs.
  • Figure 5: Total correct answers across all rounds.
  • ...and 13 more figures