Logo des Repositoriums

Auflistung nach Schlagwort "Domain-specific Languages"

1 - 2 von 2
  • Konferenzbeitrag
    Reliable Generation of Formal Specifications using Large Language Models
    (SE 2024 - Companion, 2024) Kogler, Philipp; Falkner, Andreas; Sperl, Simon
    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.
  • Konferenzbeitrag
    Workshop on the State of the Art Methods and Tools in Model-Based Systems Engineering
    (Modellierung 2022 Satellite Events, 2022) Böhm, Wolfgang; Jansen, Nico; Schmalzing, David
    This workshop aims to bring together people involved in model-based systems. In particular, through this workshop, we intended to promote the exchange between industry and research and, by linking theory and practice, exchange knowledge and experience and discuss the application of MBSE methods. Therefore, relevant topics for this workshop were experiences and challenges of applying MBSE tools, methods, and analyses, and efforts to conceive tools and methods to support MBSE.