MétaCan
Menu
Back to cohort
Record W7092191125 · doi:10.1109/ms.2025.3621625

What Inputs Drive Effective Large Language Model-Based Unit Test Generation?

2025· article· W7092191125 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueIEEE Software · 2025
Typearticle
Language
FieldComputer Science
TopicSoftware Testing and Debugging Techniques
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsUnit testingCorrectnessSoftware qualityCode coverageCode (set theory)Test (biology)Test Management ApproachTest case

Abstract

fetched live from OpenAlex

Large Language Models (LLMs) have revolutionized software engineering by automating critical tasks such as code and test generation. The effectiveness of LLM-generated tests, however, largely depends on the quality and completeness of the input context—particularly the availability of software requirements and the correctness of code under test. We study five state-of-the-art LLMs at varying scales, investigating their capabilities in generating unit test cases while focusing on how different inputs impact test correctness, bug detection capability, and code coverage. Our findings reveal that, among the LLMs studied, combining code with clear requirements produces the highest-quality test cases, whereas generating tests from incorrect code alone yields significantly poorer 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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.877
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.017
GPT teacher head0.299
Teacher spread0.281 · 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