This paper appraises recent frameworks within AI development to integrate LLMs into control tasks in automotive contexts from the perspective of safety assurance. This work has built upon the rapid integration of LLMs across automotive settings. However, we find that at present, these frameworks face significant challenges, limiting their efficacy in real-time safety-critical contexts. Firstly, we consider conceptual challenges, including the fact that deployers are faced with a dual challenge, wherein they must assure a model which has been developed upstream, i.e. as general-purpose tools by the large AI labs, in a downstream context, i.e. into specific vehicle architectures. Secondly, we consider concrete challenges from across existing standards. We show that there are currently both fundamental engineering constraints covered in ISO21448, such as latency, and novel LLM-specific issues, such as alignment-related issues covered in ISO/PAS8800. We ground both examples in a concrete introductory, experimental case study exploring an existing open-source repository, Talk2Drive. We present a safety argument in order to make explicit the limitations of existing solutions. Nonetheless, given that the use of LLMs in automotive contexts is being explored at a technical level and operationalised, we propose potential assurance mechanisms for LLM-related hazardous events going forward.

翻译：本文从安全保证的角度，评估了当前AI开发中将在汽车环境中集成LLM用于控制任务的框架。本研究基于LLM在汽车领域的快速集成背景展开。然而，我们发现当前这些框架面临重大挑战，限制了其在实时安全关键环境中的有效性。首先，我们考虑了概念性挑战，包括部署者面临的双重难题：他们必须既要保证上游开发的模型（例如，大型AI实验室作为通用工具开发）在下游环境（即集成至特定车辆架构）中的适用性。其次，我们审视了现有标准中的具体挑战。研究表明，目前存在ISO21448覆盖的基本工程约束（如延迟）以及ISO/PAS8800覆盖的新型LLM特定问题（如对齐相关的问题）。我们通过一个实际介绍性实验案例研究——探索现有开源存储库Talk2Drive——来具体说明这两个例子。我们提出了一项安全论证，以明确现有解决方案的局限性。尽管如此，鉴于LLM在汽车环境中的应用正在技术层面进行探索并逐步实施，我们提出了针对LLM相关危险事件的潜在保障机制，以供未来推进。