“Hi all - article author here. A reader of my article sent me this note, pointing me to some relevant hot-off-the-presses work (reproduced with permission): ----- A group recently evaluated the performance of Codex (and another model) on 18 programming languages: https://nuprl.github.io/MultiPL-E/ The high-order bits are: 1. The latest and greatest C…”
MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation
Large language models have demonstrated the ability to generate both natural language and programming language text. Such models open up the possibility of multi-language code generation: could code generation models generalize knowledge from one language to another? Although contemporary code generation models can generate semantically correct Python code, little is known about their abilities with other languages. We propose MultiPL-E, a system for translating unit test-driven code generation benchmarks to new languages. We create the first massively multilingual code generation benchmark by using MultiPL-E to translate two popular Python code generation benchmarks to 18 additional programming languages. We use MultiPL-E to extend the HumanEval benchmark and MBPP benchmark to 18 languages that encompass a range of programming paradigms and popularity. Using these new parallel benchmarks, we evaluate the multi-language performance of three state-of-the-art code generation models: Codex, CodeGen, and InCoder. We find that Codex matches or even exceeds its performance on Python for several other languages. The range of programming languages represented in MultiPL-E allow us to explore the impact of language frequency and language features on model performance. Finally, the MultiPL-E approach of compiling code generation benchmarks to new programming languages is both scalable and extensible, making it straightforward to evaluate new models, benchmarks, and languages.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“Based on the reverse engineering done by Parth Thakkar [1], the model used by Copilot is probably about 10x as large (12B parameters), so I would expect Copilot to still win pretty handily (especially since the Codex models are generally a lot better trained than Salesforce CodeGen or InCoder). It's also a little bit hard to compare directly because as Pa…”