Towards Reliable Generative AI-Driven Scaffolding: Reducing Hallucinations and Enhancing Quality in Self-Regulated Learning Support

TL;DR

This paper presents two novel evaluation methods for AI-generated educational scaffolds that significantly reduce hallucinations and improve quality, enhancing the reliability of self-regulated learning support systems.

Contribution

It introduces multi-agent reliability evaluation and LLM-as-a-Judge techniques to assess and improve the quality of generative AI scaffolds in education.

Findings

Reliability evaluation outperforms baselines and aligns with human judgment.

Both methods effectively reduce hallucinations in generated scaffolds.

Identified bias limitations in the LLM-as-a-Judge approach.

Abstract

Generative Artificial Intelligence (GenAI) holds a potential to advance existing educational technologies with capabilities to automatically generate personalised scaffolds that support students' self-regulated learning (SRL). While advancements in large language models (LLMs) promise improvements in the adaptability and quality of educational technologies for SRL, there remain concerns about the hallucinations in content generated by LLMs, which can compromise both the learning experience and ethical standards. To address these challenges, we proposed GenAI-enabled approaches for evaluating personalised SRL scaffolds before they are presented to students, aiming for reducing hallucinations and improving the overall quality of LLM-generated personalised scaffolds. Specifically, two approaches are investigated. The first approach involved developing a multi-agent system approach for reliability evaluation to assess the extent to which LLM-generated scaffolds accurately target relevant SRL processes. The second approach utilised the "LLM-as-a-Judge" technique for quality evaluation that evaluates LLM-generated scaffolds for their helpfulness in supporting students. We constructed evaluation datasets, and compared our results with single-agent LLM systems and machine learning approach baselines. Our findings indicate that the reliability evaluation approach is highly effective and outperforms the baselines, showing almost perfect alignment with human experts' evaluations. Moreover, both proposed evaluation approaches can be harnessed to effectively reduce hallucinations. Additionally, we identified and discussed bias limitations of the "LLM-as-a-Judge" technique in evaluating LLM-generated scaffolds. We suggest incorporating these approaches into GenAI-powered personalised SRL scaffolding systems to mitigate hallucination issues and improve the overall scaffolding quality.