On Leakage of Code Generation Evaluation Datasets

Alexandre Matton, Tom Sherborne, Dennis Aumiller, Elena Tommasone, Milad Alizadeh, Jingyi He, Raymond Ma, Maxime Voisin, Ellen Gilsenan-McMahon, Matthias Gallé


Abstract
In this paper, we consider contamination by code generation test sets, in particular in their use in modern large language models.We discuss three possible sources of such contamination and show findings supporting each of them: (i) direct data leakage, (ii) indirect data leakage through the use of synthetic data and (iii) overfitting to evaluation sets during model selection.To address this, we release Less Basic Python Problems (LBPP): an uncontaminated new benchmark of 161 prompts with their associated Python solutions. LBPP is released at https://huggingface.co/datasets/CohereForAI/lbpp
Anthology ID:
2024.findings-emnlp.772
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13215–13223
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.772
DOI:
Bibkey:
Cite (ACL):
Alexandre Matton, Tom Sherborne, Dennis Aumiller, Elena Tommasone, Milad Alizadeh, Jingyi He, Raymond Ma, Maxime Voisin, Ellen Gilsenan-McMahon, and Matthias Gallé. 2024. On Leakage of Code Generation Evaluation Datasets. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 13215–13223, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
On Leakage of Code Generation Evaluation Datasets (Matton et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.772.pdf