Analyzing the Ethical Logic of Six Large Language Models

2025-01-15

AI Summary

This study systematically evaluates the ethical reasoning capabilities of six large language models—GPT-4o, LLaMA 3.1, Claude 3.5 Sonnet, Gemini, Mistral 7B, and Perplexity—on canonical moral dilemmas including the trolley problem and the Heinz dilemma. Methodologically, we introduce a novel three-dimensional integrative framework—consequentialist–deontological–moral foundations theory—augmented by Kohlberg’s stages of moral development and explainable prompting engineering to elicit explicit justifications for model judgments. Results indicate that all models exhibit a pronounced rationalist, consequence-oriented bias, prioritizing harm minimization and fairness; their ethical discourse reaches graduate-level sophistication; cross-model logical coherence is remarkably high; and models self-assess their reasoning as surpassing typical human moral judgment. This work establishes a reproducible, decomposable evaluation paradigm for assessing and advancing ethical alignment in foundation models.

Technology Category

• Philosophy and Ethics of AI: Morality & Value-based AI
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Machine Learning: Ethics, Bias, and Fairness

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

This study examines the ethical reasoning of six prominent generative large language models: OpenAI GPT-4o, Meta LLaMA 3.1, Perplexity, Anthropic Claude 3.5 Sonnet, Google Gemini, and Mistral 7B. The research explores how these models articulate and apply ethical logic, particularly in response to moral dilemmas such as the Trolley Problem, and Heinz Dilemma. Departing from traditional alignment studies, the study adopts an explainability-transparency framework, prompting models to explain their ethical reasoning. This approach is analyzed through three established ethical typologies: the consequentialist-deontological analytic, Moral Foundations Theory, and the Kohlberg Stages of Moral Development Model. Findings reveal that LLMs exhibit largely convergent ethical logic, marked by a rationalist, consequentialist emphasis, with decisions often prioritizing harm minimization and fairness. Despite similarities in pre-training and model architecture, a mixture of nuanced and significant differences in ethical reasoning emerge across models, reflecting variations in fine-tuning and post-training processes. The models consistently display erudition, caution, and self-awareness, presenting ethical reasoning akin to a graduate-level discourse in moral philosophy. In striking uniformity these systems all describe their ethical reasoning as more sophisticated than what is characteristic of typical human moral logic.

Problem

• Ethical Decision-Making
• Moral Dilemmas
• Language Models

Innovation

• Advanced Language Models
• Moral Decision-making
• Resultism Orientation