Do AI Assistants Help Students Write Formal Specifications? A Study with ChatGPT and the B-Method

This paper investigates the role of AI assistants, specifically OpenAI's ChatGPT, in teaching formal methods (FM) to undergraduate students, using the B-method as a formal specification technique. While existing studies demonstrate the effectiveness of AI in coding tasks, no study reports on its impact on formal specifications. We examine whether ChatGPT provides an advantage when writing B-specifications and analyse student trust in its outputs. Our findings indicate that the AI does not help students to enhance the correctness of their specifications, with low trust correlating to better outcomes. Additionally, we identify a behavioural pattern with which to interact with ChatGPT which may influence the correctness of B-specifications.

Authors

Institutions

Publication Details

Published
2025-04-27
DOI
https://doi.org/10.1109/cseet66350.2025.00009
Citations
4
Primary Topic
Software Testing and Debugging Techniques
Type
article
Field-Weighted Citation Impact
9.23

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Do AI Assistants Help Students Write Formal Specifications? A Study with ChatGPT and the B-Method

Maximiliano Cristiá, Alfredo Capozucca, Albert L. Goldberg, Daniil Yampolskyi
4 citations
Software Testing and Debugging Techniques
9.23
article

Do AI Assistants Help Students Write Formal Specifications? A Study with ChatGPT and the B-Method

Maximiliano Cristiá, Alfredo Capozucca, Albert L. Goldberg, Daniil Yampolskyi
article en
4 citations

Abstract

This paper investigates the role of AI assistants, specifically OpenAI's ChatGPT, in teaching formal methods (FM) to undergraduate students, using the B-method as a formal specification technique. While existing studies demonstrate the effectiveness of AI in coding tasks, no study reports on its impact on formal specifications. We examine whether ChatGPT provides an advantage when writing B-specifications and analyse student trust in its outputs. Our findings indicate that the AI does not help students to enhance the correctness of their specifications, with low trust correlating to better outcomes. Additionally, we identify a behavioural pattern with which to interact with ChatGPT which may influence the correctness of B-specifications.

University of Luxembourg (LU), National University of Rosario (AR), Centro Internacional Franco-Argentino de Ciencias de la Información y de Sistemas (AR)
Université du Luxembourg
Quality Education
Openalex Percentile: Top 2%
Software Testing and Debugging Techniques
9.23
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.