MétaCan
Menu
Back to cohort
Record W4412703854 · doi:10.1145/3696630.3728568

Can Generative AI Produce Test Cases? An Experience from the Automotive Domain

2025· article· en· W4412703854 on OpenAlexaff
Stephen Wynn-Williams, Vera Pantelic, Mark Lawford, Claudio Menghi, Phaneendra Nalla, Hassan Artail

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsMcMaster University
FundersEuropean Commission
KeywordsAutomotive industryGenerative grammarComputer scienceTest (biology)Domain (mathematical analysis)Artificial intelligenceEngineeringMathematicsAerospace engineering

Abstract

fetched live from OpenAlex

Engineers need automated support for software testing. Generative AI is a novel technology for generating new content; however, its applicability for test case generation is still unclear. This work considers the following question: Can generative AI produce test cases in industrial software applications? We framed our question in the automotive domain. We performed our evaluation in collaboration with a large automotive manufacturer to assess to what extent generative AI can produce test cases (a.k.a. test scripts) from informal test case specifications. We considered 1) informal test case specifications defined in Rational Quality Manager, an industrial test management tool from IBM, and 2) executable test scripts specified as ecu.test packages supported by the ecu.test tool from Tracetronic. We used generative AI to produce the test scripts from the informal test case descriptions. Our results show that generative AI can produce correct or near-correct test scripts in a reasonable number of cases. We also analyzed the effects of prompt design, choice of generative AI model, and context accuracy on the effectiveness of our solution and reflected on our results.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.012
metaresearch head score (Gemma)0.056
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.012
Threshold uncertainty score0.065

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0120.056
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0020.002
Open science0.0020.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.013
GPT teacher head0.303
Teacher spread0.290 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicNatural Language Processing TechniquesFrench-language works237,207