Coverage-guided LLM test generators systematically filter out bug-revealing tests and can end up validating bugs instead of finding them.
Effective test generation using pre-trained large language models and mutation testing,
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
support 1representative citing papers
citing papers explorer
-
Design choices made by LLM-based test generators prevent them from finding bugs
Coverage-guided LLM test generators systematically filter out bug-revealing tests and can end up validating bugs instead of finding them.