Automatic Generation of Safety-compliant Linear Temporal Logic via Large Language Model: A Self-supervised Framework

[2503.15840] Automatic Generation of Safety-compliant Linear Temporal Logic via Large Language Model: A Self-supervised Framework Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Logic in Computer Science arXiv:2503.15840 (cs) [Submitted on 20 Mar 2025 ( v1 ), last revised 27 Apr 2026 (this version, v4)] Title: Automatic Generation of Safety-compliant Linear Temporal Logic via Large Language Model: A Self-supervised Framework Authors: Junle Li , Siqi Chen , Jiakai Li , Meiqi Tian , Bingzhuo Zhong View a PDF of the paper titled Automatic Generation of Safety-compliant Linear Temporal Logic via Large Language Model: A Self-supervised Framework, by Junle Li and 4 other authors View PDF HTML (experimental) Abstract: Converting high-level tasks described by natural language into formal specifications like Linear Temporal Logic (LTL) is a key step towards providing formal safety guarantees over cyber-physical systems (CPS). While the compliance of the formal specifications themselves against the safety restrictions imposed on CPS is crucial for ensuring safety, most existing works only focus on translation consistency between natural languages and formal specifications. In this paper, we introduce AutoSafeLTL, a self-supervised framework that utilizes large language models (LLMs) to automate the generation of LTL specifications complying with a set of safety restrictions while preserving their logical consistency and semantic accuracy. As a key insight, our framework integrates Language Inclusion check with an automated counterexample-guided modification mechanism to ensure the safety-compliance of the resulting LTL specifications. In particular, we develop 1) an LLM-as-an-Aligner, which performs atomic proposition matching between generated LTL specifications and safety restrictions to enforce semantic alignment; and 2) an LLM-as-a-Critic, which automates LTL specification refinement by interpreting counterexamples derived from Language Inclusion checks. Experimental results demonstrate that our architecture effectively guarantees safety-compliance for the generated LTL specifications, achieving a 0% violation rate against imposed safety restrictions. This shows the potential of our work in synergizing AI and formal verification techniques, enhancing safety-aware specification generation and automatic verification for both AI and critical CPS applications. Subjects: Logic in Computer Science (cs.LO) ; Formal Languages and Automata Theory (cs.FL) Cite as: arXiv:2503.15840 [cs.LO] (or arXiv:2503.15840v4 [cs.LO] for this version) https://doi.org/10.48550/arXiv.2503.15840 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Junle Li [ view email ] [v1] Thu, 20 Mar 2025 04:40:29 UTC (5,772 KB) [v2] Thu, 24 Apr 2025 06:30:19 UTC (5,639 KB) [v3] Fri, 10 Apr 2026 11:26:43 UTC (1,211 KB) [v4] Mon, 27 Apr 2026 10:42:41 UTC (1,214 KB) Full-text links: Access Paper: View a PDF of the paper titled Automatic Generation of Safety-compliant Linear Temporal Logic via Large Language Model: A Self-supervised Framework, by Junle Li and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LO < prev | next > new | recent | 2025-03 Change to browse by: cs cs.FL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents#1118731
• Policy-Grounded Safety Evaluation of 20 Large Language Models#183283
• Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models#1014066
• Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models#978372
• Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack#1117452