Software Testing with Large Language Models: An Interview Study with Practitioners
Bibliographic record
Abstract
Background: The use of large language models in software testing is growing fast as they support numerous tasks, from test case generation to automation, and documentation. However, their adoption often relies on informal experimentation rather than structured guidance. Aims: This study investigates how software testing professionals use LLMs in practice to propose a preliminary, practitioner-informed guideline to support their integration into testing workflows. Method: We conducted a qualitative study with 15 software testers from diverse roles and domains. Data were collected through semi-structured interviews and analyzed using grounded theory-based processes focused on thematic analysis. Results: Testers described an iterative and reflective process that included defining testing objectives, applying prompt engineering strategies, refining prompts, evaluating outputs, and learning over time. They emphasized the need for human oversight and careful validation, especially due to known limitations of LLMs such as hallucinations and inconsistent reasoning. Conclusions: LLM adoption in software testing is growing, but remains shaped by evolving practices and caution around risks. This study offers a starting point for structuring LLM use in testing contexts and invites future research to refine these practices across teams, tools, and tasks.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.038 | 0.060 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.007 | 0.008 |
| Scholarly communication | 0.005 | 0.007 |
| Open science | 0.002 | 0.007 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".