.png){kind=icon}
.png){kind=icon}
Return
Large Language Models in Code Co-generation for Safe Autonomous Vehicles
.png){kind=icon}
PRE
AI
DOI：10.1007/978-3-032-01241-8_13.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 LLMgenerated code, we propose an evaluation pipeline to conduct sanitychecks on the generated code. We compare the performance of six stateof-the-art LLMs (CodeLlama, CodeGemma, DeepSeek-r1, DeepSeekCoders, 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.
Keywords:
DevOps
Autonomous Driving System
Automated Code Generation
Large Language Mo del
Verification
Simulation
Journal
C
IF:
0
Papers:
15
Citations:
0