HYU-NLP/KR-HumanEval
收藏Hugging Face2025-06-03 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/HYU-NLP/KR-HumanEval
下载链接
链接失效反馈官方服务：
资源简介：
KR-HumanEval Benchmark是HumanEval基准的韩文版本，原始的文档字符串被翻译成韩文。使用DeepL翻译API进行翻译，并在翻译后进行了手动后处理和基于LLM的质量评估。数据格式和性能评估方法与HumanEval相同。相关论文分析了使用KR-HumanEval的的语言模型在韩语程序合成性能。
KR-HumanEval Benchmark is the Korean version of the HumanEval benchmark, where the original docstrings are translated into Korean. The translation was performed using the DeepL translator API, followed by manual post-processing and LLM-based quality evaluation. The data format and the method of benchmark performance evaluation are identical to those of HumanEval.
提供机构：
HYU-NLP
