SOURCE-LINKED INTELLIGENCE

Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Most work in computational ethics treats annotator disagreement on moral content as noise to be voted away, collapsed into majority vote or the more permissive any-annotator rule the moment a single annotator flags an item. We argue this uncertainty should instead be modeled and learned from. We introduce Moral Entropy, a Bayesian framework that keeps a full posterior over the true label and decomposes its entropy into aleatoric uncertainty (irreducible disagreement about the moral content) and epistemic uncertainty (from insufficient or noisy annotation) -- and lets any heuristic consensus ru

Read original source ↗ Open in workspace

recordType

paper

region

Global