This dissertation aims to make specification recovery from imperfect code accurate, evidence-driven, and uncertainty-aware, so that it consistently yields effective bug-finding tests.
Jun-Da Zhao· Companion Proceedings of the...· 0 citations
A specification-based unit test generation paradigm that replaces the code under test in the prompt with an LLM-generated specification docstring is introduced, showing that this paradigm effectively reduces misguided tests while substantially increasing effective tests, improves multi-round, feedback-driven test gener...
It is found that the usefulness of coverage and mutation is highly context-dependent: in regression-style settings where the code provided to the LLM can be reasonably assumed bug-free, these metrics can provide meaningful signals when comparing across models; in another common scenario where the code-under-test may al...