Metraipolis › archive › dc_e712eec2ba0f

Automatic Translation of Unstructured Requirements into Linear Temporal Logic through Large Language Models — arXiv:2608.06287

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06287
License (as archived)
CC0-1.0
Archived
2026-10-27T08:10:16.722Z
SHA-256 of the archived text
65e7b340886a8c931e423880e81be783213625d8feea355a45c48297d810b275
Stable URL of this page
https://metraipolis.com/documento/dc_e712eec2ba0f

How to cite

Automatic Translation of Unstructured Requirements into Linear Temporal Logic through Large Language Models — arXiv:2608.06287 — arXiv (en), https://arxiv.org/abs/2608.06287 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e712eec2ba0f (Metraipolis archive dc_e712eec2ba0f, sha256 65e7b340886a8c931e423880e81be783213625d8feea355a45c48297d810b275)
BibTeX
@misc{dce712eec2ba0f,
  title = {Automatic Translation of Unstructured Requirements into Linear Temporal Logic through Large Language Models — arXiv:2608.06287},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06287},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e712eec2ba0f; sha256 65e7b340886a8c931e423880e81be783213625d8feea355a45c48297d810b275},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06287. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automatically translating unstructured natural language requirements into formal specifications remains a challenge in requirements engineering and formal methods, particularly for safety- and mission-critical systems whose verification depends on mathematically precise specifications. This paper evaluates whether contemporary off-the-shelf Large Language Models (LLMs) can help bridge this gap by generating Linear Temporal Logic (LTL) formulas directly from unstructured requirements. The study examines six modern LLMs using a few-shot prompting strategy on a heterogeneous benchmark of 15 structurally varied requirements. Five independent generations were collected for each requirement-model pair, yielding 450 candidate LTL formulas in total. Performance was assessed through manual semantic evaluation, pass@k for k in {1, 3, 5}, and a self-consistency measure capturing syntactic reproducibility across stochastic trials. The results indicate that current general-purpose LLMs can achieve practically significant performance on the unstructured NL-to-LTL task without task-specific fine-tuning. The study also considers understandability for non-experts by pairing generated formulas with model-produced natural language explanations and discussing the complementary use of timeline-based LTL visualization. The findings suggest that modern LLMs are becoming viable front-end assistants for semi-automated formalization workflows.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-07 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.06287 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-27T07:55:47.052Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).