Authors: Matton, Alexandre and Sherborne, Tom and Aumiller, Dennis and Tommasone, Elena and Alizadeh, Milad and He, Jingyi and Ma, Raymond and Voisin, Maxime and Gilsenan-McMahon, Ellen and Gallé, Matthias
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
Link: Read Paper
Labels: code generation, program synthesis, benchmark