Using GPT-4 to cluster test reports by bug type and then round-robin selecting across clusters yields faster discovery of distinct bugs, a 12.77% average APFD gain over DeepPrior.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Redefining Crowdsourced Test Report Prioritization: An Innovative Approach with Large Language Model
Using GPT-4 to cluster test reports by bug type and then round-robin selecting across clusters yields faster discovery of distinct bugs, a 12.77% average APFD gain over DeepPrior.