arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.01573cs.SEcs.AIcs.LGcs.LO
收藏

LLM支持的Java验证的下一步

Next Steps in LLM-Supported Java Verification

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Samuel Teuber, Bernhard Beckert

AI总结:

本文初步展示如何利用演绎验证的严格工具集,从不可靠的LLM预言机中可靠地引导出正确的Java代码规约注解,为大规模软件系统提供可证明的正确性保证。

摘要:

近期研究表明,大型语言模型(LLMs)不仅是代码生成的合适工具,还能生成基于注解的代码规约。扩展这些方法或可推导出大规模软件系统的可证明正确性保证。与其他LLM任务相比,演绎验证领域具有显著优势:能提供严格工具集来检验LLM生成的解。本文初步展示了如何利用该严格工具集,从不可靠的LLM预言机中可靠地引导出正确的规约注解。

英文摘要:

Recent work has shown that Large Language Models (LLMs) are not only a suitable tool for code generation but also capable of generating annotation-based code specifications. Scaling these methodologies may allow us to deduce provable correctness guarantees for large-scale software systems. In comparison to other LLM tasks, the application field of deductive verification has the notable advantage of providing a rigorous toolset to check LLM-generated solutions. This short paper provides early results on how this rigorous toolset can be used to reliably elicit correct specification annotations from an unreliable LLM oracle.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑