Moralytics

non-profit

https://www.moralytics.org

AI & ML interests

AI-powered moral inference, tuned on Haidt's Moral Foundation Theory.

Recent Activity

maciejskorski authored a paper 19 days ago

Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora

maciejskorski authored a paper 19 days ago

Exact Bias of Linear TRNG Correctors -- Spectral Approach

Senseterna authored a paper about 1 month ago

"Many Are My Names": The Anatomy of the Assistant and Its Personas via Sparse Autoencoders

View all activity

authored 2 papers 19 days ago

Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora

Paper • 2605.22660 • Published May 21 • 1

Exact Bias of Linear TRNG Correctors -- Spectral Approach

Paper • 2509.26393 • Published Sep 30, 2025

authored a paper about 1 month ago

"Many Are My Names": The Anatomy of the Assistant and Its Personas via Sparse Autoencoders

Paper • 2608.07852 • Published Aug 14

updated a Space 4 months ago

README

published a Space 4 months ago

README

authored a paper about 1 year ago

Beyond Human Judgment: A Bayesian Evaluation of LLMs' Moral Values Understanding

Paper • 2508.13804 • Published Aug 19, 2025 • 4