Exploring LLMs for generating synthetic test data
Organization
Software Engineering Analytics
Abstract
Testing in a production-like environment is a crucial part of software quality assurance. However, many public sector organizations are not allowed to use actual production data for testing due to privacy concerns. One alternative is to use synthetically generated data that is rich enough to simulate a wide range of user scenarios. This thesis explores the potential of various LLM-based techniques for generating synthetic test data for a System Under Test (SUT) and evaluates the quality and effectiveness of the generated data for testing purposes. The specific SUT can be selected in consultation with the interested student.
Graduation Theses defence year
2024-2025
Supervisor
Faiz Ali Shah
Spoken language (s)
English
Requirements for candidates
Level
Masters
Keywords
Application of contact
Name
Faiz Ali Shah
Phone
E-mail