Automatically Testing Functional Properties of Code Translation Models. (arXiv:2309.12813v2 [cs.SE] UPDATED)

Large language models are becoming increasingly practical for translating
code across programming languages, a process known as $transpiling$. Even
though automated transpilation significantly boosts developer productivity, a
key concern is whether the generated code is correct. Existing work initially
used manually crafted test suites to test the translations of a small corpus of
programs; these test suites were later automated. In contrast, we devise the
first approach for automated, functional, property-based testing of code
translation models. Our general, user-provided specifications …

arxiv automated code cs.se developer developer productivity functional generated key language language models languages large language large language models practical process productivity programming programming languages test testing translation work