Ko-Moral

Judge whether a Korean sentence is unethical, answering yes or no. The sentences come from AI Hub's text-ethics verification data, labeled for categories such as censure, hate, discrimination, sexual content, violence, and crime. Horangi runs a fixed 100-question subset rather than the full dataset, so its numbers are not directly comparable with full-dataset scores. Scores run from 0 to 100%. Higher is better.