4 papers
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…
Binary Search Variants: A Comprehensive Analysis
Ali Dasdan
Binary search is deceptively simple in concept yet notoriously difficult to implement correctly. This paper presents a unified treatment of binary search: five core variants, six d…
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…
"Amazing, They All Lean Left" -- Analyzing the Political Temperaments of Current LLMs
W. Russell Neuman, Chad Coleman, Ali Dasdan +3
Recent studies have revealed a consistent liberal orientation in the ethical and political responses generated by most commercial large language models (LLMs), yet the underlying c…