论文进阶
explainable AI
可解释 AI（XAI）：能够为自身输出提供人类可理解的解释/理由的 AI 技术和系统，目的是帮助用户理解模型、建立合适信任、避免盲目接受或拒绝。
English Definition
"AI systems and methods (often abbreviated XAI) that produce human-interpretable justifications for their outputs, in order to support user understanding, trust, and appropriate reliance."
用法说明 · 针对中文母语者
在 HCI/CHI 论文里 XAI 常被进一步批评——研究发现'带解释'并不等于'用户真的会正确使用解释'，于是近年出现 rely calibration、intelligent reasoning cues 等新框架。
真实用例 · 2 条
"Keywords: Clinical Reasoning, AI-Assisted Decision-Making, Decision Support, Explainable AI"
论文Pipeline extracted — review needed·论文关键词
"These findings can help us understand why some reasoning cues embedded in AI decision support systems are effective and others are not, especially when the cues were originally intended to calibrate reliance (such as AI explanations)."
论文Pipeline extracted — review needed·讨论部分：反思 XAI 的作用
由 pipeline 自动采集，待人工 review