LTLGuard: Formalizing LTL Specifications with Compact Language Models and Lightweight Symbolic Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912946344427520 |
|---|---|
| author | Andresel, Medina Mateis, Cristinel Nickovic, Dejan Kounoupidis, Spyridon Katsaros, Panagiotis Tripakis, Stavros |
| author_facet | Andresel, Medina Mateis, Cristinel Nickovic, Dejan Kounoupidis, Spyridon Katsaros, Panagiotis Tripakis, Stavros |
| contents | Translating informal requirements into formal specifications is challenging due to the ambiguity and variability of natural language (NL). This challenge is particularly pronounced when relying on compact (small and medium) language models, which may lack robust knowledge of temporal logic and thus struggle to produce syntactically valid and consistent formal specifications. In this work, we focus on enabling resource-efficient open-weight models (4B--14B parameters) to generate correct linear temporal logic (LTL) specifications from informal requirements. We present LTLGuard, a modular toolchain that combines constrained generation with formal consistency checking to generate conflict-free LTL specifications from informal input. Our method integrates the generative capabilities of model languages with lightweight automated reasoning tools to iteratively refine candidate specifications, understand the origin of the conflicts and thus help in eliminating inconsistencies. We demonstrate the usability and the effectiveness of our approach and perform quantitative evaluation of the resulting framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05728 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LTLGuard: Formalizing LTL Specifications with Compact Language Models and Lightweight Symbolic Reasoning Andresel, Medina Mateis, Cristinel Nickovic, Dejan Kounoupidis, Spyridon Katsaros, Panagiotis Tripakis, Stavros Logic in Computer Science Artificial Intelligence Software Engineering Translating informal requirements into formal specifications is challenging due to the ambiguity and variability of natural language (NL). This challenge is particularly pronounced when relying on compact (small and medium) language models, which may lack robust knowledge of temporal logic and thus struggle to produce syntactically valid and consistent formal specifications. In this work, we focus on enabling resource-efficient open-weight models (4B--14B parameters) to generate correct linear temporal logic (LTL) specifications from informal requirements. We present LTLGuard, a modular toolchain that combines constrained generation with formal consistency checking to generate conflict-free LTL specifications from informal input. Our method integrates the generative capabilities of model languages with lightweight automated reasoning tools to iteratively refine candidate specifications, understand the origin of the conflicts and thus help in eliminating inconsistencies. We demonstrate the usability and the effectiveness of our approach and perform quantitative evaluation of the resulting framework. |
| title | LTLGuard: Formalizing LTL Specifications with Compact Language Models and Lightweight Symbolic Reasoning |
| topic | Logic in Computer Science Artificial Intelligence Software Engineering |
| url | https://arxiv.org/abs/2603.05728 |