Analyzing the Ethical Logic of Six Large Language Models
This research addresses the problem of understanding and comparing ethical reasoning in LLMs for AI safety and alignment researchers, though it is incremental as it applies existing ethical frameworks to new models.
This study analyzed the ethical reasoning of six large language models using moral dilemmas and found that they exhibit largely convergent, rationalist, and consequentialist logic, with decisions prioritizing harm minimization and fairness, while also showing nuanced differences across models.
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.