Paul Röttger

Latest

• The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising 'Alignment' in Large Language Models
• SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models
• XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
• The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values
• Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
• The Ecological Fallacy in Annotation: Modeling Human Label Variation goes beyond Sociodemographics
• Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
• Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
• Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks