BriefGPT.xyz
Jan, 2023
半真实 XAI 的先前工作、需求和基准
Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI
HTML
PDF
Saugat Aryal, Mark T Keane
TL;DR
该论文调查了历史和最近在可解释人工智能(XAI)和半事实(semi-factuals)领域的突破，定义了半事实XAI的主要要求，并报告了历史算法的基准测试（以及一种新颖的，朴素的方法），为未来的算法发展提供了坚实的基础。
Abstract
Recently,
explainable ai
(XAI) research has focused on
counterfactual explanations
as post-hoc justifications for AI-system decisions (e.g. a customer refused a loan might be told: If you asked for a loan with a
→