BeaverTails

Dataset Card for BeaverTails BeaverTails is an AI safety-focused collection comprising a series of datasets. This repository includes human-labeled data consisting of question-answer (QA) pairs, each identified with their corresponding harm categories. It should be noted that a single QA pair can be associated with mor

Papers using BeaverTails (3)

Do Large Language Models Reflect Demographic Pluralism in Safety?2026Too Helpful, Too Harmless, Too Honest or Just Right?2025We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong2025