LARGE LANGUAGE MODELS IN TEST TASKS DEVELOPMENT

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.

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2025-05-25
DOI
https://doi.org/10.5281/zenodo.15512500
Primary Topic
Intelligent Tutoring Systems and Adaptive Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

LARGE LANGUAGE MODELS IN TEST TASKS DEVELOPMENT

Zenodo (CERN European Organization for Nuclear Research)
Intelligent Tutoring Systems and Adaptive Learning
article

LARGE LANGUAGE MODELS IN TEST TASKS DEVELOPMENT

article en

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.

Zenodo (CERN European Organization for Nuclear Research)
Slovak University of Technology in Bratislava (SK)
Quality Education
Openalex Percentile: Top 76%
Intelligent Tutoring Systems and Adaptive Learning
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

LARGE LANGUAGE MODELS IN TEST TASKS DEVELOPMENT · Zenodo (CERN European Organization for Nuclear Research) (2025) | TGRS Research Map | TGRS