Generating Machine-Processable Specifications from Natural Language Using Large Language Models in Automotive Commissioning and Testing

2026-01-0768

To be published on 06/01/2026

Authors
Abstract
Content
The commissioning of electric and electronic components contributes significantly to adding value in vehicle production. Moreover, testing these components and digital vehicle functions secures this value and ensures high-quality products. The emergence of software-defined vehicles, however, leads to an increased scope and complexity of commissioning and testing processes as software functions depend on electric and electronic components that take on perception, execution, and processing tasks. Nevertheless, assembly planning must still meet the requirement of providing thorough, error-free, yet cost-effective processes. In this context, this paper tackles a common challenge: Software that is deployed in vehicle production to implement commissioning and testing processes is developed upon specifications that define prerequisites, procedures, and target end results in unstructured natural language. Therefore, extensive manual translation into executable code is needed, being susceptible to errors as well as time-consuming. The large amount of vehicle configurations and rapid changes in vehicle software further complicate the development of commissioning and testing software, particularly as verbose textual dependency descriptions risk impairing comprehensibility. The automated generation of commissioning and testing software based on machine-processable specifications could consequently ensure consistency, reduce manual effort, and accelerate the development process. For this purpose, we examine the processability of commissioning and testing specifications in natural language and the transferability of the included requirements into a machine-processable form. First, a schema for a machine-processable notation of commissioning and testing requirements is introduced. Secondly, several large language models are evaluated in practical trials, based on their ability to transfer existing specifications written in natural language into the previously presented schema. In summary, this study aims at enabling more efficient software development based on textual requirements. This work offers valuable insights into the suitability and applicability of large language models within the planning of automotive commissioning and testing processes, targeting enhanced automation and efficiency.
Meta TagsDetails
Citation
Köhler, K., El Asad, A., Hahn, M., and Reuss, H., "Generating Machine-Processable Specifications from Natural Language Using Large Language Models in Automotive Commissioning and Testing," 2026 Stuttgart International Symposium, Stuttgart, Germany, July 8, 2026, .
Additional Details
Publisher
Published
To be published on Jun 1, 2026
Product Code
2026-01-0768
Content Type
Technical Paper
Language
English