Feb. 28, 2024, 5:49 a.m. | Li Zhong, Zilong Wang, Jingbo Shang

cs.CL updates on arXiv.org arxiv.org

arXiv:2402.16906v1 Announce Type: cross
Abstract: Large language models (LLMs) are leading significant progress in code generation. Beyond one-pass code generation, recent works further integrate unit tests and program verifiers into LLMs to iteratively refine the generated programs. However, these works consider the generated programs as an indivisible entity, which falls short for LLMs in debugging the programs, especially when the programs contain complex logic flows and data operations. In contrast, when human developers debug programs, they typically set breakpoints and …

abstract arxiv beyond code code generation cs.ai cs.cl cs.se debugger generated language language model language models large language large language model large language models llms progress refine step-by-step tests type via

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne