LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark

arXiv:2609.00192 · cs.AI, cs.CL, cs.CV, cs.CY · Submitted 2026-08-31 · Read on arXiv

cs.AI, cs.CL, cs.CV, cs.CY

Submitted: 2026-08-31

Updated: 2026-08-31

Code: https://github.com/IremYoldas/LLM-Driven-AVPedestrian-Bias

Terminology

• Autonomous Vehicle — 12× in this paper
• Benchmark — 10× in this paper · explained in 2 episodes
• Accountability — 3× in this paper · explained in 2 episodes
• All Else Being Equal — 3× in this paper
• Consistency — 3× in this paper · explained in 3 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Self-consistency — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Activation Steering — 1× in this paper · explained in 4 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• IEEE Intelligent Vehicles Symposium — 1× in this paper
• Joint Attention — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Synthetic Data Generation — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving
• Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
• RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
• Toxicity in ChatGPT: Analyzing Persona-assigned Language Models
• StereoSet: Measuring stereotypical bias in pretrained language models
• LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions
• Current state of LLM Risks and AI Guardrails
• A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models
• Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges
• Age and gender bias in pedestrian detection algorithms
• Joint Attention in Autonomous Driving (JAAD)
• Qwen3-VL Technical Report
• Qwen3 Technical Report
• The Llama 3 Herd of Models
• Mistral 7B
• GPT-4o System Card
• SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
• The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection