Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

natural-language-processing-8

Code Repair

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in code-repair-16

Trend

Dataset

Best Model

Actions

CodeXGLUE - Bugs2Fix

Libraries

Use these libraries to find code-repair-16 models and implementations

Datasets

CodeXGLUE

PyTorrent

FixEval

Performance Improving Code Edits (PIE)

CriticBench

DISL

Subtasks

No subtasks available.

Most implemented papers

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin B. Clement, Dawn Drain, Daxin Jiang, Duyu Tang, Ge Li, Lidong Zhou, Linjun Shou, Long Zhou, Michele Tufano, Ming Gong, Ming Zhou, Nan Duan, Neel Sundaresan, Shao Kun Deng, Shengyu Fu, Shujie Liu•Mon Feb 08 2021

This paper introduces CodeXGLUE, a benchmark dataset to foster machine learning research for program understanding and generation that includes a collection of 10 tasks across 14 datasets and a platform for model evaluation and comparison.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

1327 0

Paper Graph

Learning Performance-Improving Code Edits

Graham Neubig, A. Yazdanbakhsh, Milad Hashemi, Uri Alon, Aman Madaan, Alexander Shypula, Parthasarathy Ranganathan, Yiming Yang•Tue Feb 14 2023

This paper investigates the ability of large language models (LLMs) to suggest functionally correct, performance improving code edits, and hypothesizes that language models can suggest such edits in ways that would be impractical for static analysis alone.

128 0

Paper Graph

OctoPack: Instruction Tuning Code Large Language Models

Qi Liu, Xiangru Tang, Niklas Muennighoff, S. Longpre, Qian Liu, Qinkai Zheng, L. V. Werra, Binyuan Hui, A. Zebaze, Terry Yue Zhuo, Swayam Singh•Sun Aug 13 2023

The authors' models, OctoCoder and OctoGeeX, achieve the best performance across HumanEvalPack among all permissive models, demonstrating CommitPack's benefits in generalizing to a wider set of languages and natural coding tasks.

190 0

Paper Graph

Break-It-Fix-It: Unsupervised Learning for Program Repair

Michihiro Yasunaga, Percy Liang•Thu Jun 10 2021

This work proposes a new training approach, Break-It-Fix-It (BIFI), which uses the critic to check a fixer's output on real bad inputs and add good (fixed) outputs to the training data, and trains a breaker to generate realistic bad code from good code.

123 0

Paper Graph

Guiding Language Models of Code with Global Context using Monitors

Aditya Kanade, Navin Goyal, Shuvendu K. Lahiri, Lakshya A Agrawal, S. Rajamani•Sun Jun 18 2023

This work proposes a notion of monitors that use static analysis in the background to guide the decoding of language models of code, and shows that monitor-guided decoding consistently improves the ability of an LM to not only generate identifiers that match the ground truth but also improves compilation rates and agreement with ground truth.

34 0

Paper Graph

INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair

Zhenghao Liu, Shuo Wang, Zhiyuan Liu, Ge Yu, Ganqu Cui, Ning Ding, Hanbin Wang•Wed Nov 15 2023

InterVENOR is a system designed to emulate the interactive code repair processes observed in humans, encompassing both code diagnosis and code repair, and can accurately identify syntax errors and assertion errors and provide precise instructions to repair codes.

21 0

Paper Graph

MACER: A Modular Framework for Accelerated Compilation Error Repair

Darshak Chhatbar, Umair Z. Ahmed, Purushottam Kar•Wed May 27 2020

MACER is a novel technique for accelerated error repair based on a modular segregation of the repair process into repair identification and repair application that outperforms existing methods by 20% at suggesting fixes for popular errors while being competitive or better at other errors.

17 0

Paper Graph

Adding a benchmark result helps the community track progress.

Code Repair | State-of-the-Art