摘要：
人工智能技术具有颠覆性，给人类生产、生活带来革命性影响，但人工智能系统的不透明性影响用户信任，也难以保障技术的安全性和可靠性。阐释人工智能技术、揭示人工智能的运行逻辑至关重要。人工智能技术的风险性、不透明性是人工智能系统的固有属性，通过立足于内在主义与外在主义相结合的技术伦理进路以及规范性和描述性相结合的应用伦理进路，可以揭示可解释人工智能的因果相关关系，构建基于因果相关性的可解释人工智能模型，发展负责任的人工智能。
关键词:
可解释性,
可阐释性,
可解释人工智能,
负责任的人工智能
Abstract:
Artificial Intelligence (AI) technology is subversive, which has a revolutionary impact on human
production and life, but the opacity of its system affects user trust, and it is difficult to ensure the security
andreliability of AI technology. It is very important to explain AI technology and reveal the operation logic of
AI. The risk attribute and opacity derived from AI technology are the inherent attributes of AI system. Through
the technical ethics approach based on the combination of internalism and externalism, and the application
ethics approach based on the combination of standardization and description, we can reveal the causal
correlation of explainable artificial intelligence, and build an explainable artificial intelligence model based on causal correlation.
Key words:
explainable,
interpretability,
explainable AI,
responsible AI
闫坤如. 构建中国阐释学（十三）：人工智能阐释|可解释人工智能：本源、进路与实践[J]. 探索与争鸣, 2022(8): 102-109.
Yan Kunru. Explainable Artificial Intelligence: Origin, Approach and Practice[J]. Exploration and Free Views, 2022(8): 102-109.