ivada-infra/DOCS
3
0
Fork 0
Code Issues 1 Pull Requests 5 Actions Packages Projects Releases Wiki Activity
DOCS/research/explainability/miller_2019_explanation_in_ai.md
happybell80 725ad0876c fix: 문서 파일 실행 권한 제거 
- 모든 .md, .html 파일 권한을 644로 정상화
- .gitignore 파일 권한도 644로 수정
- 문서 파일에 실행 권한은 불필요하고 보안상 바람직하지 않음
- deprecated 아이디어 폴더 생성 및 레벨별 UI 변경 아이디어 이동
2025-08-18 00:37:51 +09:00

609 B
Raw Blame History

Explanation in Artificial Intelligence: Insights from the Social Sciences

  • Author: Tim Miller
  • Year: 2019
  • Summary: This influential paper argues that to be effective, XAI must be grounded in how humans actually explain things to each other. Drawing from philosophy, psychology, and cognitive science, Miller argues that good explanations are contrastive (explaining why P happened instead of Q), selective (not exhaustive), and social (part of a conversation). This provides crucial principles for designing user-centric explanation interfaces.
  • Link: https://arxiv.org/abs/1706.07269