This is a multi-region infilling version of the C++ translation of HumanEval. It was generated by randomly removing between 1 and 3 spans from the canonical solution in the dataset.
This dataset was used for evaluation in the paper Constrained Decoding of Diffusion LLMs with Context-Free Grammars. You can find the corresponding evaluation code on the project GitHub Repository.
dataset =… See the full description on the dataset page:
https://huggingface.co/datasets/eth-sri/HumanEval-MRI-Cpp.