header.html

An official website of the European Union How do you know?      
European Commission logo

handle.jsp

cover
Automated test generation tools often produce assertions that reflect implemented behavior, limiting their usage to regression testing. In this paper, we propose LLMPROPHET, a black-box approach that trains LLMs on automatically generated regression tests using Few-Shot Learning to identify non-regression faults without relying on source code. By employing iterative cross-validation and a leave-one-out strategy, LLMPROPHET identifies regression assertions that are misaligned with expected behaviors. We outline LLMPROPHET’s workflow, feasibility, and preliminary findings, demonstrating its potential for LLM-driven fault detection.
2025-08-21
IEEE Computer Society
JRC141000
2159-4848 (online),   
https://doi.ieeecomputersociety.org/10.1109/ICSTW64639.2025.10962503,    https://publications.jrc.ec.europa.eu/repository/handle/JRC141000,   
10.1109/ICSTW64639.2025.10962503 (online),   
NameCountryCityType
Datasets
IDTitlePublic URL
Dataset collections
IDAcronymTitlePublic URL
Scripts / source codes
DescriptionPublic URL
Additional supporting files
File nameDescriptionFile type 

footer.html