Structured Gherkin prompts increased executability and pass rate of LLM-generated tests in two small benchmarks compared to plain natural-language prompts.
Gherkin reference,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Private GPTs for LLM-driven testing in software development and machine learning
Structured Gherkin prompts increased executability and pass rate of LLM-generated tests in two small benchmarks compared to plain natural-language prompts.