Transforming Natural Language Requirements to Formalism Using LLMs
Systems Engineering · 2026-03 · 29 (2) · 195-204
DOI: 10.1002/sys.70023 ↗Kurz gefasst
Fachartikel in der Zeitschrift Systems Engineering, online erschienen am 16.12.2025. Verfasst von Baoluo Meng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Defense Advanced Research Projects Agency.
Abstract (Originalsprache)
Logical formalism is the use of mathematical models, logical symbols and operators, and logical reasoning to express ideas precisely and unambiguously. Such precision is needed in systems engineering to avoid misunderstandings and misinterpretations. However, creating logical formalism requires a deep understanding of formal logics, making it inaccessible to individuals without specialized training. The complexity of logical formalism also makes it time‐consuming and costly to develop, thus acting as a barrier for practitioners seeking to apply formalism in their domains. To make formalism more approachable, we present, implement, and evaluate a large language model (LLM)–based approach to interactively translate unstructured natural language (NL) requirements to logical formalism. Our translation strategy employs a NL‐based interface that provides high assurance for translation correctness while still being approachable for nonexperts in formal methods. We demonstrate the effectiveness of our tool through an experimental evaluation of an industry use case—landing gear.
Förderung
- Defense Advanced Research Projects Agency
Zitieren
APA
Meng, B., Lorch, R., Siu, K., Durling, M., Varanasi, S. C., Paul, S., & Moitra, A. (2026). Transforming Natural Language Requirements to Formalism Using LLMs. Systems Engineering, 29(2), 195-204. https://doi.org/10.1002/sys.70023
Vancouver
Meng B, Lorch R, Siu K, Durling M, Varanasi SC, Paul S, et al. Transforming Natural Language Requirements to Formalism Using LLMs. Systems Engineering. 2026;29(2):195-204. doi:10.1002/sys.70023
BibTeX
@article{Meng2026,
author = {Meng, Baoluo and Lorch, Robert and Siu, Kit and Durling, Michael and Varanasi, Sarat Chandra and Paul, Saswata and Moitra, Abha},
title = {Transforming Natural Language Requirements to Formalism Using LLMs},
journal = {Systems Engineering},
year = {2026},
volume = {29},
number = {2},
pages = {195--204},
doi = {10.1002/sys.70023}
}
EUVIMED