
AI의 잘못된 정보 생성과 사용자의 신뢰 형성AI Hallucination & Trust
AI가 사실과 다른 정보를 생성할 때, 사람들이 AI를 얼마나 신뢰해야 할지 판단하도록 돕는 인터페이스를 설계합니다.How can we design interfaces that help people judge how much to trust AI when it generates inaccurate information?
관련 논문Related Publications
- AIES '25Hide or Highlight: Understanding the Impact of Factuality Expression on User Trust
- AIES '25Highlight All the Phrases: Enhancing LLM Transparency through Visual Factuality Indicators
- ACL '25Multi-Level Explanations for Generative Language Models
- CSCW '24Evaluating What Others Say: The Effect of Accuracy Assessment in Shaping Mental Models of AI Systems



