Large-scale moral machine experiment on large language models

TL;DR

This study evaluates 52 large language models' moral decision-making in autonomous driving, revealing that larger models tend to align more with human ethics, but updates and ethical emphasis vary, impacting practical deployment.

Contribution

It provides a comprehensive comparison of diverse LLMs' moral judgments, analyzing factors like size, updates, and architecture, to inform ethical AI development in autonomous systems.

Findings

Proprietary and large open-source models align closely with human moral judgments.

Model size negatively correlates with distance from human preferences in open-source models.

Model updates do not consistently improve moral judgment alignment.

Abstract

The rapid advancement of Large Language Models (LLMs) and their potential integration into autonomous driving systems necessitates understanding their moral decision-making capabilities. While our previous study examined four prominent LLMs using the Moral Machine experimental framework, the dynamic landscape of LLM development demands a more comprehensive analysis. Here, we evaluate moral judgments across 52 different LLMs, including multiple versions of proprietary models (GPT, Claude, Gemini) and open-source alternatives (Llama, Gemma), to assess their alignment with human moral preferences in autonomous driving scenarios. Using a conjoint analysis framework, we evaluated how closely LLM responses aligned with human preferences in ethical dilemmas and examined the effects of model size, updates, and architecture. Results showed that proprietary models and open-source models exceeding 10 billion parameters demonstrated relatively close alignment with human judgments, with a significant negative correlation between model size and distance from human judgments in open-source models. However, model updates did not consistently improve alignment with human preferences, and many LLMs showed excessive emphasis on specific ethical principles. These findings suggest that while increasing model size may naturally lead to more human-like moral judgments, practical implementation in autonomous driving systems requires careful consideration of the trade-off between judgment quality and computational efficiency. Our comprehensive analysis provides crucial insights for the ethical design of autonomous systems and highlights the importance of considering cultural contexts in AI moral decision-making.