Fine-tuned Mistral-7b, Llama2-7b, and CodeLlama-7b classify flaky test root causes in C++ and Java, with Mistral-7b reporting perfect scores on a small augmented C++ dataset.
Continuous practices and devops: beyond the buzz, what does it all mean?,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Large Language Model Approach to Identify Flakiness in C++ Projects
Fine-tuned Mistral-7b, Llama2-7b, and CodeLlama-7b classify flaky test root causes in C++ and Java, with Mistral-7b reporting perfect scores on a small augmented C++ dataset.