Supporting Student Decisions on Learning Recommendations: An LLM-Based Chatbot with Knowledge Graph Contextualization for Conversational Explainability and Mentoring

TL;DR

This paper presents an LLM-based chatbot that uses a knowledge graph to provide controlled, explainable learning recommendations and facilitate student-mentor conversations, aiming to enhance understanding and decision-making in educational settings.

Contribution

It introduces a novel chatbot framework combining LLMs with knowledge graph contextualization for improved conversational explainability in learning recommendations.

Findings

The chatbot effectively supports student understanding of recommendations.

The knowledge graph constrains LLM outputs for safer explanations.

User study demonstrates potential and limitations of the approach.

Abstract

Student commitment towards a learning recommendation is not separable from their understanding of the reasons it was recommended to them; and their ability to modify it based on that understanding. Among explainability approaches, chatbots offer the potential to engage the student in a conversation, similar to a discussion with a peer or a mentor. The capabilities of chatbots, however, are still not sufficient to replace a human mentor, despite the advancements of generative AI (GenAI) and large language models (LLM). Therefore, we propose an approach to utilize chatbots as mediators of the conversation and sources of limited and controlled generation of explanations, to harvest the potential of LLMs while reducing their potential risks at the same time. The proposed LLM-based chatbot supports students in understanding learning-paths recommendations. We use a knowledge graph (KG) as a human-curated source of information, to regulate the LLM's output through defining its prompt's context. A group chat approach is developed to connect students with human mentors, either on demand or in cases that exceed the chatbot's pre-defined tasks. We evaluate the chatbot with a user study, to provide a proof-of-concept and highlight the potential requirements and limitations of utilizing chatbots in conversational explainability.