Large Language Models in Code Co-generation for Safe Autonomous Vehicles
Paper i proceeding, 2026
Software engineers in various industrial domains are already using Large Language Models (LLMs) to accelerate the process of implementing parts of software systems. When considering its potential use for ADAS or AD systems in the automotive context, there is a need to systematically assess this new setup: LLMs entail a well-documented set of risks for safety-related systems’ development due to their stochastic nature. To reduce the effort for code reviewers to evaluate LLM-generated code, we propose an evaluation pipeline to conduct sanity-checks on the generated code. We compare the performance of six state-of-the-art LLMs (CodeLlama, CodeGemma, DeepSeek-r1, DeepSeek-Coders, Mistral, and GPT-4) on four safety-related programming tasks. Additionally, we qualitatively analyse the most frequent faults generated by these LLMs, creating a failure-mode catalogue to support human reviewers. Finally, the limitations and capabilities of LLMs in code generation, and the use of the proposed pipeline in the existing process, are discussed.
Large Language Model
DevOps
Verification
Simulation
Autonomous Driving System
Automated Code Generation
Författare
Ali Nouri
Göteborgs universitet
Chalmers, Data- och informationsteknik, Interaktionsdesign och Software Engineering
Volvo Group
Beatriz Cabrero-Daniel
Chalmers, Data- och informationsteknik, Interaktionsdesign och Software Engineering
Göteborgs universitet
Zhennan Fei
Chalmers, Elektroteknik, System- och reglerteknik
Volvo Group
Krishna Ronanki
Chalmers, Data- och informationsteknik, Interaktionsdesign och Software Engineering
Göteborgs universitet
Håkan Sivencrona
Volvo Group
Christian Berger
Göteborgs universitet
Chalmers, Data- och informationsteknik, Interaktionsdesign och Software Engineering
Lecture Notes in Computer Science
0302-9743 (ISSN) 1611-3349 (eISSN)
Vol. 15954 LNCS 193-2089783032012401 (ISBN)
44th International Conference on Computer Safety, Reliability and Security, SAFECOMP 2025
Stockholm, Sweden,
Stockholm, Sweden,
Ämneskategorier (SSIF 2025)
Programvaruteknik
Datorsystem
DOI
10.1007/978-3-032-01241-8_13