Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback

arXiv:2311.07215v2 Announce Type: replace
Abstract: Code editing is an essential step towards reliable program synthesis to automatically correct critical errors generated from code LLMs. Recent studies have demonstrated that closed-source LLMs (i.e., ChatGPT and GPT-4) are capable of generating corrective feedback to edit erroneous inputs. However, it remains challenging for open-source code LLMs to generate feedback for code editing, since these models tend to adhere to the superficial formats of feedback and provide feedback with misleading information. Hence, the focus …

arxiv boost bugs code code llms coffee cs.cl cs.se feedback llms type