Generating and Evaluating Tests for K-12 Students with Language Model Simulations: A Case Study on Sentence Reading Efficiency

TL;DR

This paper presents a method using fine-tuned large language models to generate and evaluate parallel reading efficiency tests for K-12 students, reducing costs and time while maintaining high reliability and correlation with expert-designed tests.

Contribution

It introduces a novel approach combining GPT-4 generated items, LLM filtering, and optimal transport techniques to create high-quality parallel tests for educational assessment.

Findings

Generated tests closely match original test difficulty and reliability.

High correlation (r=0.93) with standard expert-designed tests.

Effective for students from grades 2 to 8.

Abstract

Developing an educational test can be expensive and time-consuming, as each item must be written by experts and then evaluated by collecting hundreds of student responses. Moreover, many tests require multiple distinct sets of questions administered throughout the school year to closely monitor students' progress, known as parallel tests. In this study, we focus on tests of silent sentence reading efficiency, used to assess students' reading ability over time. To generate high-quality parallel tests, we propose to fine-tune large language models (LLMs) to simulate how previous students would have responded to unseen items. With these simulated responses, we can estimate each item's difficulty and ambiguity. We first use GPT-4 to generate new test items following a list of expert-developed rules and then apply a fine-tuned LLM to filter the items based on criteria from psychological measurements. We also propose an optimal-transport-inspired technique for generating parallel tests and show the generated tests closely correspond to the original test's difficulty and reliability based on crowdworker responses. Our evaluation of a generated test with 234 students from grades 2 to 8 produces test scores highly correlated (r=0.93) to those of a standard test form written by human experts and evaluated across thousands of K-12 students.