114. Evaluation of Ethical Dilemmas in ChatGPT-Based Decision-Making o…

International Oral Session, International, 27(금) 13:20-15:00, 라카이볼룸Ⅰ 

Evaluation of Ethical Dilemmas in ChatGPT-Based Decision-Making of Autonomous Vehicles / Zixuan Xu(Korea Advanced Institute of Science and Technology), Neha Sengar(Korea Advanced Institute of Science and Technology), Tiantian Chen(Korea Advanced Institute of Science and Technology)

Large Language Models have attracted global attention for their capabilities in knowledge acquisition and human-like reasoning. Although LLMs have demonstrated feasibility in performing autonomous driving tasks in simulated and real-world environments, questions remain regarding their safety and ethical decision-making. To address this, we propose a novel framework for evaluating and interpreting the ethical decision-making mechanism of LLM-driven autonomous vehicles. Our study investigates the ethical dilemma of whether to prioritize saving pedestrians or passengers, inspired by the Moral Machine Experiment. We used a stated preference survey to include factors to create 13,122 choice scenarios (a full factorial design) to analyze responses from advanced LLMs. Our findings reveal significant differences in the decision-making process and preferences for saving road users among these LLMs. This study provides valuable insights into ethical considerations in AI systems and thus facilitates the responsible development of AI in autonomous vehicles.