PulseAugur
中
实时 07:25:32
English(EN) ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation

ClassEval-Pro基准测试揭示LLM在类级别代码生成方面存在困难

研究人员推出了ClassEval-Pro,这是一个旨在评估大型语言模型类级别代码生成能力的新基准测试。该基准测试包含11个领域的300个任务,通过一个自动化的流程创建,该流程集成了复杂性增强和来自2025年1月之后更新的GitHub存储库的真实代码。对五个前沿LLM的初步评估显示,即使是表现最好的模型,其Pass@1也仅达到45.6%,这凸显了在组合代码创建方面存在的重大挑战,其中逻辑和依赖性错误是主要问题。 AI

影响 新的基准测试突出了LLM在类级别代码生成方面的局限性,重点关注逻辑和依赖性错误。

排序理由 引入了一个用于评估LLM代码生成能力的新基准测试。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

ClassEval-Pro基准测试揭示LLM在类级别代码生成方面存在困难

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
引入了一个用于评估LLM代码生成能力的新基准测试。
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
162 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    ClassEval-Pro:用于类级别代码生成的跨域基准测试

    LLMs have achieved strong results on both function-level code synthesis and repository-level code modification, yet a capability that falls between these two extremes -- compositional code creation, i.e., building a complete, internally structured class from a specification -- re…