Synthetic Programming Elicitation and Repair for Text-to-Code in Very Low-Resource Programming Languages

arXiv:2406.03636v1 Announce Type: cross
Abstract: Recent advances in large language models (LLMs) for code applications have demonstrated remarkable zero-shot fluency and instruction following on challenging code related tasks ranging from test case generation to self-repair. Unsurprisingly, however, models struggle to compose syntactically valid programs in programming languages unrepresented in pre-training, referred to as very low-resource Programming Languages (VLPLs). VLPLs appear in crucial settings including domain-specific languages for internal to tools and tool-chains and legacy languages. Inspired by an HCI technique …

abstract advances applications arxiv case code compose cs.lg cs.pl however language language models languages large language large language models llms low programming programming languages repair struggle synthetic tasks test test case text text-to-code type zero-shot