Shadowgraph
About
Sign in

HYU-NLP/Revisiting-Modularity

Official Repository for "Revisiting the Impact of Pursuing Modularity for Code Generation"

16

stars

3

commits

Python

primary language

Oct 10, 2024

updated

README

Revisiting the Impact of Pursuing Modularity for Code Generation

Official Repository for "Revisiting the Impact of Pursuing Modularity for Code Generation" [Paper(arXiv)]

Deokyeong Kang, Kijung Seo, Taeuk Kim. Accepted to EMNLP 2024 Findings

Contents

  • apps: source codes for APPS dataset
    • In-Context Learning: icl.py
  • codecontests: source codes for CodeContests dataset
    • Modularity score (MoS) metric: utils/utils.py
    • In-Context Learning: icl.py
    • Fine-tuning: ft.py
    • Correlation experiment: icl_corr.py
    • Perplexity experiment: ppl.py

Contributors

kdy20401

2 commits

tjrlwjd1

1 commits

Similar repos

vinci-grape/APO

This is the repository for the paper titled "Aligning with Human Coding Preferences for Improving…

0

hendrycks/apps

APPS: Automated Programming Progress Standard (NeurIPS 2021)

538

microsoft/CodeT

678

automl/is_mamba_capable_of_icl

18

salesforce/CodeRL

This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models…

575

s2e-lab/Datasets-Quality

An empirical investigation of quality in code benchmark datasets; Accepted at SCAM 2024.

0

NathanaelBeau/CodeInsight

The CodeInsight dataset is designed for code generation tasks, providing developers with…

15

sssszh/CodePLAN

The code repository for the paper “Enhancing Code Generation Performance of Smaller Models by…

8

Languages

Python

77.3%

Jupyter Notebook

14.9%

Shell

7.7%

HYU-NLP/Revisiting-Modularity

Official Repository for "Revisiting the Impact of Pursuing Modularity for Code Generation"

16

stars

3

commits

Python

primary language

Oct 10, 2024

updated

README

Revisiting the Impact of Pursuing Modularity for Code Generation

Official Repository for "Revisiting the Impact of Pursuing Modularity for Code Generation" [Paper(arXiv)]

Deokyeong Kang, Kijung Seo, Taeuk Kim. Accepted to EMNLP 2024 Findings

Contents

  • apps: source codes for APPS dataset
    • In-Context Learning: icl.py
  • codecontests: source codes for CodeContests dataset
    • Modularity score (MoS) metric: utils/utils.py
    • In-Context Learning: icl.py
    • Fine-tuning: ft.py
    • Correlation experiment: icl_corr.py
    • Perplexity experiment: ppl.py

Similar repos

vinci-grape/APO

This is the repository for the paper titled "Aligning with Human Coding Preferences for Improving…

0

hendrycks/apps

APPS: Automated Programming Progress Standard (NeurIPS 2021)

538

microsoft/CodeT

678

automl/is_mamba_capable_of_icl

18

salesforce/CodeRL

This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models…

575

s2e-lab/Datasets-Quality

An empirical investigation of quality in code benchmark datasets; Accepted at SCAM 2024.

0

NathanaelBeau/CodeInsight

The CodeInsight dataset is designed for code generation tasks, providing developers with…

15

sssszh/CodePLAN

The code repository for the paper “Enhancing Code Generation Performance of Smaller Models by…

8

Contributors

kdy20401

2 commits

tjrlwjd1

1 commits

Languages

Python

77.3%

Jupyter Notebook

14.9%

Shell

7.7%