Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moon, Seungjun, Chae, Hyungjoo, Song, Yongho, Kwon, Taeyoon, Kang, Dongjin, Ong, Kai Tzu-iunn, Hwang, Seung-won, Yeo, Jinyoung
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911782497419264
author Moon, Seungjun
Chae, Hyungjoo
Song, Yongho
Kwon, Taeyoon
Kang, Dongjin
Ong, Kai Tzu-iunn
Hwang, Seung-won
Yeo, Jinyoung
author_facet Moon, Seungjun
Chae, Hyungjoo
Song, Yongho
Kwon, Taeyoon
Kang, Dongjin
Ong, Kai Tzu-iunn
Hwang, Seung-won
Yeo, Jinyoung
contents 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 of our work is to leverage open-source code LLMs to generate helpful feedback with correct guidance for code editing. To this end, we present Coffee, a collected dataset specifically designed for code fixing with feedback. Using this dataset, we construct CoffeePots, a framework for COde Fixing with FEEdback via Preference-Optimized Tuning and Selection. The proposed framework aims to automatically generate helpful feedback for code editing while minimizing the potential risk of superficial feedback. The combination of Coffee and CoffeePots marks a significant advancement, achieving state-of-the-art performance on HumanEvalFix benchmark. Codes and model checkpoints are publicly available at https://github.com/Lune-Blue/COFFEE.
format Preprint
id arxiv_https___arxiv_org_abs_2311_07215
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback
Moon, Seungjun
Chae, Hyungjoo
Song, Yongho
Kwon, Taeyoon
Kang, Dongjin
Ong, Kai Tzu-iunn
Hwang, Seung-won
Yeo, Jinyoung
Computation and Language
Software Engineering
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 of our work is to leverage open-source code LLMs to generate helpful feedback with correct guidance for code editing. To this end, we present Coffee, a collected dataset specifically designed for code fixing with feedback. Using this dataset, we construct CoffeePots, a framework for COde Fixing with FEEdback via Preference-Optimized Tuning and Selection. The proposed framework aims to automatically generate helpful feedback for code editing while minimizing the potential risk of superficial feedback. The combination of Coffee and CoffeePots marks a significant advancement, achieving state-of-the-art performance on HumanEvalFix benchmark. Codes and model checkpoints are publicly available at https://github.com/Lune-Blue/COFFEE.
title Coffee: Boost Your Code LLMs by Fixing Bugs with Feedback
topic Computation and Language
Software Engineering
url https://arxiv.org/abs/2311.07215