arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.30163eess.SYcs.SY
收藏

基于端到端抽象的控制与LLM增强的NL到LTL翻译

End-to-End Abstraction-Based Control with LLM-Enhanced NL-to-LTL Translation

UCLouvain(瓦隆天主教大学);University of Michigan(密歇根大学);University of Oxford(牛津大学)

Amir Bayat, Necmiye Ozay, Alessandro Abate, Raphael M. Jungers

AI总结:

提出LLM增强的NL-to-LTL翻译管道,集成到ABCD框架中,并通过实验揭示翻译成功率与LTL公式复杂度的缩放规律。

摘要:

基于抽象的控制设计(ABCD)为复杂信息物理系统(CPSs)的安全控制提供了一个原则性框架,但将现实世界需求与其形式化综合机制对接仍然是一个主要瓶颈:这些需求最自然地以自然语言(NL)表达,而ABCD需要诸如线性时序逻辑(LTL)等形式化规约。大型语言模型(LLMs)通过将NL需求翻译为形式化规约,为弥合这一差距提供了有前景的方法。本文做出三项贡献。首先,我们形式化了一个LLM增强的ABCD管道,其中NL需求被翻译为LTL并用于形式化综合工作流。其次,我们在Dionysos工具箱中实现了该管道,并引入了一个基准测试,用于在逻辑多样性和语言变化下评估NL-to-LTL翻译。第三,通过使用最先进的LLMs进行实验,我们表明翻译准确性随着目标规约变得更加复杂而系统性下降,衡量指标包括抽象语法树(AST)大小、时间深度和Büchi自动机大小,同时考虑NL输入长度。这些结果揭示了一个缩放定律,将LLM成功率与底层LTL公式的内在复杂性联系起来。这些贡献共同提供了一个评估框架和一条实用的集成路径,使ABCD更易访问,同时保持形式化方法的严谨性。

英文摘要:

Abstraction-Based Controller Design (ABCD) offers a principled framework for the safe control of complex Cyber-Physical Systems (CPSs), but interfacing real-world requirements with its formal synthesis machinery remains a major bottleneck: such requirements are most naturally expressed in Natural Language (NL), whereas ABCD requires formal specifications such as Linear Temporal Logic (LTL). Large Language Models (LLMs) offer a promising way to bridge this gap by translating NL requirements into formal specifications. This paper makes three contributions. First, we formalize an LLM-enhanced pipeline for ABCD, in which NL requirements are translated into LTL and used within a formal synthesis workflow. Second, we implement this pipeline in the Dionysos toolbox and introduce a benchmark for evaluating NL-to-LTL translation under both logical diversity and linguistic variation. Third, experiments with state-of-the-art LLMs reveal a consistent relationship between LTL complexity and translation success: translation accuracy decreases as the target specification becomes more complex in terms of Abstract Syntax Tree (AST) size, temporal depth, and Büchi automaton size, while accounting for NL input length. Together, these contributions provide both an evaluation framework and a practical integration pathway for making ABCD more accessible while preserving the rigor of formal methods.

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。

↑