5 papers · 1 filter
Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning
Ali Dasdan, Manan Shah, W. Russell Neuman +3
Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it. We use Transluce, an AI-driven mechanistic-inter…
Six Llamas: Comparative Religious Ethics Through LoRA-Adapted Language Models
Chad Coleman, W. Russell Neuman, Manan Shah +5
We present Six Llamas, a comparative study examining whether large language models fine-tuned on distinct religious corpora encode systematically different patterns of ethical reas…
The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approach
Chad Coleman, W. Russell Neuman, Ali Dasdan +2
As large language models (LLMs) are increasingly deployed in consequential decision-making contexts, systematically assessing their ethical reasoning capabilities becomes a critica…
Auditing the Ethical Logic of Generative AI Models
W. Russell Neuman, Chad Coleman, Ali Dasdan +2
As generative AI models become increasingly integrated into high-stakes domains, the need for robust methods to evaluate their ethical reasoning becomes increasingly important. Thi…
Analyzing the Ethical Logic of Eight Large Language Models
W. Russell Neuman, Chad Coleman, Manan Shah
This study examines the expressed ethical logic of eight prominent large language models from OpenAI, Meta, Perplexity, Anthropic, Google, Mistral, DeepSeek, and xAI. Each model an…