Large Language Models in Code Co-generation for Safe Autonomous Vehicles
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908380062285824 |
|---|---|
| author | Nouri, Ali Cabrero-Daniel, Beatriz Fei, Zhennan Ronanki, Krishna Sivencrona, Håkan Berger, Christian |
| author_facet | Nouri, Ali Cabrero-Daniel, Beatriz Fei, Zhennan Ronanki, Krishna Sivencrona, Håkan Berger, Christian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19658 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large Language Models in Code Co-generation for Safe Autonomous Vehicles Nouri, Ali Cabrero-Daniel, Beatriz Fei, Zhennan Ronanki, Krishna Sivencrona, Håkan Berger, Christian Software Engineering Artificial Intelligence 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. |
| title | Large Language Models in Code Co-generation for Safe Autonomous Vehicles |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2505.19658 |