Can I read Barabadi Et Al-2025-Frontiers in Artificial Intelligence on EtoBox?

Barabadi Et Al-2025-Frontiers in Artificial Intelligence by pepehux is a document available to read on EtoBox.

What is Barabadi Et Al-2025-Frontiers in Artificial Intelligence about?

This research investigates the moral reasoning patterns of two large language models (LLMs), ChatGPT and Claude Sonnet, in comparison to human responses to moral dilemmas. The findings indicate that LLMs exhibit context-sensitive moral judgments, alternating between deontological and utilitarian perspectives, challenging the assumption that they predominantly favor utilitarianism. Understanding these patterns is crucial for fostering societal trust in AI systems, especially in ethically sensitive domains.

Author

pepehux

Language

EN