English(EN) Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding

语言模型通过数据流预训练改进静态程序切片

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-01 04:00

研究人员开发了Sliceformer，一种使用语言模型识别相关代码段的新型静态程序切片方法。该方法通过数据流感知预训练改进依赖建模并防止约束解码产生不准确的输出，从而解决了现有基于学习的技术的局限性。在Java和Python基准测试上的评估表明，Sliceformer的性能显著优于当前方法，ExactMatch准确率提高了22%。 AI

影响提高了自动化代码分析的准确性，可能有助于开发人员调试和理解复杂的代码库。

排序理由介绍一种新颖的静态程序切片方法的学术论文。

在 arXiv cs.AI 阅读 →

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

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; 介绍一种新颖的静态程序切片方法的学术论文。
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, product; 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: 122 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]

arXiv cs.AI TIER_1 English(EN) · Pengfei He (Peter), Shaowei Wang (Peter), Tse-Hsun (Peter), Chen, Muhammad Asaduzzaman · 2026-05-01 04:00

使用具有数据流感知预训练和约束解码的语言模型的静态程序切片

arXiv:2604.26961v1 Announce Type: cross Abstract: Static program slicing is a fundamental software engineering technique for isolating code relevant to specific variables. While recent learning-based approaches using language models (LMs) show promise in automating slice predicti…

本文如何被排名

报道来源 [1]

使用具有数据流感知预训练和约束解码的语言模型的静态程序切片

相关实体

相关话题