Gavin Abercrombie

Latest

• Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution
• Subjective isms? On the Danger of Conflating Hate and Offence in Abusive Language Detection
• Mirages. On Anthropomorphism in Dialogue Systems
• Temporal and Second Language Influence on Intra-Annotator Agreement and Stability in Hate Speech Labelling
• Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design
• SAFETYKIT: First Aid for Measuring Safety in Open-domain Conversational Systems