moral-reasoning

ErisML is a modeling language for governed, foundation-model-enabled agents operating in pervasive computing environments

Framework-pluralist compiler from natural-language moral material to a typed MoralGraph and DEME-evaluable ErisML IR — four ethical lenses, no silent aggregation, hash-chained DecisionProofs

Moral Spectrum Analyzer — measures the moral coverage of AI content-evaluation, moderates where validated, escalates where not, and discovers missing dimensions. GTC 2026 prototype (Pillar A).

Papers, Research Experiments and Results on Non-Abelian Gauge Structure in Stratified Quantum Normative Dynamics

The Conscience Layer Prototype, created by Aleksandar Rodić in 2025, establishes a research foundation for ethical artificial intelligence. It brings moral awareness into computation through principles of truth, human autonomy, and societal responsibility, defining a transparent and accountable form of intelligence.

Dear Ethicist — an advice column game measuring the group structure of moral reasoning (V4 measured, D4 posited), based on the NA-SQND framework

Geometric Ethics - The Mathematical Structure of Moral Reasoning (Book 3 of the Geometric Series)

Ethical Decision Simulator: audit how LLMs reason through moral dilemmas—multi-model compare, ethical lens stress tests, semantic agreement metrics, and exportable JSON verdicts. Python, Streamlit, Groq or Ollama—deployed on Streamlit Cloud.

Multilingual Story Moral AI Leaderboard

A mathematical framework for auditing whether LLMs execute or rationalize moral rules under irreversibility constraints.

This repository introduces the AraIslaMorals framework, utilized to investigate the alignment of Large Language Models (LLMs) with Arabic-Islamic moral values through three complementary methodologies.

Moral personas playing iterated prisoner's dilemma with LLM agents. Trajectories and metrics released on HuggingFace Datasets.