McEval: Massively Multilingual Code Evaluation
Beihang University · Beijing University of Aeronautics and Astronautics · The University of British Columbia · Nanjing University · University of Waterloo · College of Computer Science, Beijing Information Science and Technology University · Shanghai Jiao Tong University · Institute of automation, Chinese academy of science, Chinese Academy of Sciences
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Code large language models (LLMs) have shown remarkable advances in code understanding, completion, and generation tasks. Programming benchmarks, comprised of a selection of code challenges and corresponding test cases, serve as a standard to evaluate the capability of different LLMs in such tasks. However, most existing benchmarks primarily focus on Python and are still restricted to a limited number of languages, where other languages are translated from the Python samples degrading the data diversity. To further facilitate the research of code LLMs, we propose a massively multilingual code benchmark covering 40 programming languages (McEval) with 16K test samples, which substantially pushes the limits of code LLMs in multilingual scenarios. The benchmark contains challenging code completion, understanding, and generation evaluation tasks with finely curated massively multilingual instruction corpora McEval-Instruct. In addition, we introduce an effective multilingual coder mCoder trained on McEval-Instruct to support multilingual programming language generation. Extensive experimental results on McEval show that there is still a difficult journey between open-source models and closed-source LLMs in numerous languages. The instruction corpora and evaluation benchmark are available at https://github.com/MCEVAL/McEval.