Konferenzbeitrag
Reliable Generation of Formal Specifications using Large Language Models
Vorschaubild nicht verfügbar
Volltext URI
Dokumententyp
Text/Conference Paper
Dateien
Zusatzinformation
Datum
2024
Autor:innen
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Quelle
Verlag
Gesellschaft für Informatik e.V.
Zusammenfassung
Recent pre-trained Large Language Models (LLMs) have demonstrated promising Natural Language Processing (NLP) and code generation abilities. However, the intrinsically unreliable output due to the probabilistic nature of LLMs imposes a major challenge as validity can generally not be guaranteed, making subsequent processing prone to errors. When LLMs are used to translate natural-language specifications to formal specifications, this limitation becomes evident. We propose a framework involving prompting and algorithmic post-processing that continuously interacts with the LLM to ensure strict syntactic validity and reasonable content correctness. Furthermore, we introduce a use-case in the domain of engineering processes for railway infrastructure and demonstrate that our approach is sufficiently mature for implementation in an industrial environment.