# DriveSafe: A Hierarchical Risk Taxonomy for Safety-Critical LLM-Based Driving Assistants

arXiv: https://arxiv.org/abs/2601.12138 · HTML: https://mlsanity.com/paper/2601.12138/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Large language models for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 6 of its 41 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## Placed in

- End-to-end autonomous driving / [Large language models for driving](https://mlsanity.com/driving/large-language-models-for-driving/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 6 of 6)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Receive, Reason, and React: Drive as You Say with Large Language Models in Autonomous Vehicles](https://mlsanity.com/paper/2310.08034/) (2023)
- [TrustAgent: Towards Safe and Trustworthy LLM-based Agents](https://mlsanity.com/paper/2402.01586/) (2024)
- [SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering](https://mlsanity.com/paper/2408.11491/) (2024)
- [Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning](https://mlsanity.com/paper/2507.04250/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization](https://mlsanity.com/paper/2609.19630/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly integrated into vehicle-based digital assistants, where unsafe, ambiguous, or legally incorrect responses can lead to serious safety, ethical, and regulatory consequences. Despite growing interest in LLM safety, existing taxonomies and evaluation frameworks remain largely general-purpose and fail to capture the domain-specific risks inherent to real-world driving scenarios. In this paper, we introduce DriveSafe, a hierarchical, four-level risk taxonomy designed to systematically characterize safety-critical failure modes of LLM-based driving assistants. The taxonomy comprises 129 fine-grained atomic risk categories spanning technical, legal, societal, and ethical dimensions, grounded in real-world driving regulations and safety principles and reviewed by domain experts. To validate the safety relevance and realism of the constructed prompts, we evaluate their refusal behavior across six widely deployed LLMs. Our analysis shows that the evaluated models often fail to appropriately refuse unsafe or non-compliant driving-related queries, underscoring the limitations of general-purpose safety alignment in driving contexts.