To what extent do deep learning-based code recommenders generate predictions by cloning code from the training set?-Reference-Cited by-同舟云学术

To what extent do deep learning-based code recommenders generate predictions by cloning code from the training set?

Published:2022-05-23 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 19th International Conference on Mining Software Repositories
language:
Short-container-title:

Author:

Ciniselli Matteo¹,Pascarella Luca¹,Bavota Gabriele¹

Affiliation:

1. Università della Svizzera italiana, Switzerland

Funder

European Research Council

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3524842.3528440

Reference60 articles.

1. Milton Allamanis. [n.d.]. CodeSearchNet Deduplication Algorithm. https://github.com/github/CodeSearchNet/blob/master/src/dataextraction/dedup_split.py. Milton Allamanis. [n.d.]. CodeSearchNet Deduplication Algorithm. https://github.com/github/CodeSearchNet/blob/master/src/dataextraction/dedup_split.py.

2. The adverse effects of code duplication in machine learning models of code

3. Uri Alon , Roy Sadaka , Omer Levy , and Eran Yahav . 2020 . Structural language models of code . In International Conference on Machine Learning. PMLR, 245--256 . Uri Alon, Roy Sadaka, Omer Levy, and Eran Yahav. 2020. Structural language models of code. In International Conference on Machine Learning. PMLR, 245--256.

4. Anon. 2022. Replication Package https://github.com/DLCloning/DLClone.git. Anon. 2022. Replication Package https://github.com/DLCloning/DLClone.git.

5. Gareth Ari Aye and Gail E Kaiser . 2020. Sequence Model Design for Code Completion in the Modern IDE. arXiv preprint arXiv:2004.05249 ( 2020 ). Gareth Ari Aye and Gail E Kaiser. 2020. Sequence Model Design for Code Completion in the Modern IDE. arXiv preprint arXiv:2004.05249 (2020).

Cited by 12 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?;Proceedings of the ACM on Software Engineering;2024-07-12

2. Generating and Reviewing Programming Codes with Large Language Models: A Systematic Mapping Study;Proceedings of the 20th Brazilian Symposium on Information Systems;2024-05-20

3. MicroRec: Leveraging Large Language Models for Microservice Recommendation;Proceedings of the 21st International Conference on Mining Software Repositories;2024-04-15

4. On the Generalizability of Deep Learning-based Code Completion Across Programming Language Versions;Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension;2024-04-15

5. A User-centered Security Evaluation of Copilot;Proceedings of the IEEE/ACM 46th International Conference on Software Engineering;2024-04-12