LLM Prompt Evaluation for Educational Applications

TL;DR

This paper introduces a systematic, evidence-based framework for evaluating and comparing prompts used in large language models for educational purposes, demonstrated through a tournament-style assessment of prompt templates.

Contribution

It presents a generalizable evaluation methodology using a tournament framework and Glicko2 ratings to assess prompt effectiveness in educational LLM applications.

Findings

A strategic reading prompt outperformed others with up to 100% win probability.

The evaluation framework can be adapted for various educational LLM tasks.

Prompt design incorporating pedagogical strategies improves question quality.

Abstract

As large language models (LLMs) become increasingly common in educational applications, there is a growing need for evidence-based methods to design and evaluate LLM prompts that produce personalized and pedagogically aligned out-puts. This study presents a generalizable, systematic approach for evaluating prompts, demonstrated through an analysis of LLM-generated follow-up questions in a structured dialogue activity. Six prompt templates were designed and tested. The templates incorporated established prompt engineering patterns, with each prompt emphasizing distinct pedagogical strategies. The prompt templates were compared through a tournament-style evaluation framework that can be adapted for other educational applications. The tournament employed the Glicko2 rating system with eight judges evaluating question pairs across three dimensions: format, dialogue support, and appropriateness for learners. Data was sourced from 120 authentic user interactions across three distinct educational deployments. Results showed that a single prompt related to strategic reading out-performed other templates with win probabilities ranging from 81% to 100% in pairwise comparisons. This prompt combined persona and context manager pat-terns and was designed to support metacognitive learning strategies such as self-directed learning. The methodology showcases how educational technology re- searchers can systematically evaluate and improve prompt designs, moving beyond ad-hoc prompt engineering toward evidence-based prompt development for educational applications.