“Also see; Unsupervised Evaluation of Code LLMs with Round-Trip Correctness - https://arxiv.org/abs/2402.08699 Code repository for the above - https://github.com/google-deepmind/icml2024-roundtrip-correctness RTCE: RoundTrip Code Evaluation Framework - https://www.emergentmind.com/topics/roundtripcodeeval-rtce”
Unsupervised Evaluation of Code LLMs with Round-Trip Correctness
To evaluate code large language models (LLMs), research has relied on a few small manually curated benchmarks, such as HumanEval and MBPP, which represent a narrow part of the real-world software domains. In this work, we introduce round-trip correctness (RTC) as an alternative evaluation method. RTC allows Code LLM evaluation on a broader spectrum of real-world software domains without the need for costly human curation. RTC rests on the idea that we can ask a model to make a prediction (e.g., describe some code using natural language), feed that prediction back (e.g., synthesize code from the predicted description), and check if this round-trip leads to code that is semantically equivalent to the original input. We show how to employ RTC to evaluate code synthesis and editing. We find that RTC strongly correlates with model performance on existing narrow-domain code synthesis benchmarks while allowing us to expand to a much broader set of domains and tasks which was not previously possible without costly human annotations.
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- Unsupervised Evaluation of Code LLMs with Round-Trip Correctness ↗PaulHoule · 2024-02-21 · 2 分