Evaluating LLM-Generated Q&A Test: a Student-Centered Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wróblewska, Anna, Grabek, Bartosz, Świstak, Jakub, Dan, Daniel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908480629112832
author Wróblewska, Anna
Grabek, Bartosz
Świstak, Jakub
Dan, Daniel
author_facet Wróblewska, Anna
Grabek, Bartosz
Świstak, Jakub
Dan, Daniel
contents This research prepares an automatic pipeline for generating reliable question-answer (Q&A) tests using AI chatbots. We automatically generated a GPT-4o-mini-based Q&A test for a Natural Language Processing course and evaluated its psychometric and perceived-quality metrics with students and experts. A mixed-format IRT analysis showed that the generated items exhibit strong discrimination and appropriate difficulty, while student and expert star ratings reflect high overall quality. A uniform DIF check identified two items for review. These findings demonstrate that LLM-generated assessments can match human-authored tests in psychometric performance and user satisfaction, illustrating a scalable approach to AI-assisted assessment development.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06591
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating LLM-Generated Q&A Test: a Student-Centered Study
Wróblewska, Anna
Grabek, Bartosz
Świstak, Jakub
Dan, Daniel
Computation and Language
Human-Computer Interaction
This research prepares an automatic pipeline for generating reliable question-answer (Q&A) tests using AI chatbots. We automatically generated a GPT-4o-mini-based Q&A test for a Natural Language Processing course and evaluated its psychometric and perceived-quality metrics with students and experts. A mixed-format IRT analysis showed that the generated items exhibit strong discrimination and appropriate difficulty, while student and expert star ratings reflect high overall quality. A uniform DIF check identified two items for review. These findings demonstrate that LLM-generated assessments can match human-authored tests in psychometric performance and user satisfaction, illustrating a scalable approach to AI-assisted assessment development.
title Evaluating LLM-Generated Q&A Test: a Student-Centered Study
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2505.06591