An empirical study reports that ChatGPT-4o Turbo generates mostly valid system test cases from SRS documents, with about 15% of valid tests being novel, but its redundancy detection has a 30% false positive rate.
Title resolution pending
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
System Test Case Design from Requirements Specifications: Insights and Challenges of Using ChatGPT
An empirical study reports that ChatGPT-4o Turbo generates mostly valid system test cases from SRS documents, with about 15% of valid tests being novel, but its redundancy detection has a 30% false positive rate.