Work

Large Language Models in Test Tasks Development

Year: 2025

Type: conference-paper

Abstract: This study presents practical experiences with the use of Large Language Models (LLMs) in creating mathematics-based tests for automated university-level examinations. Two wellknown LLM-powered chat tools, ChatGPT and Perplexity Pro, were tested using identical prompts to generate a predefined set of mathematical test questions. We discuss effective prompting strategies and analyze errors in the generated outputs. Additionally, we provide a brief evaluation and offer recommendations based on our findings.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.15512499

Authors: Červeňanská, Zuzana, Markechová, Iveta, Kotianová, Janette

Institution: Slovak University of Technology in Bratislava

Language: English

Topic: Artificial Intelligence in Education

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: green

OpenAlex ID: W6912029901

FWCI:

Cites:

Cited by:

Related to: