经验法则:使用部分信息解释人工智能系统
Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information
浏览论文内容
中文总结 AI 辅助
该研究提出名为“经验法则”(RoT)的新型XAI方法,可识别特定数据点下与AI系统行为最相关的特征,适用于零样本分类等场景,符合AI法规且效率更高。
中文摘要 AI 辅助
可解释人工智能(XAI)旨在解释人工智能(AI)系统如何得出特定决策。我们提出“经验法则”(RoT)解释,这是一种基于新公式的XAI新方法,用于识别特定数据点下与预测AI系统行为最相关的特征。我们证明RoT适用于以下XAI场景:(a)使用大语言模型(LLM)的零样本分类,(b)无需模型访问的不透明AI系统审计,(c)科学发现中的AI应用。此外,RoT符合领先AI法规的特定要求,为XAI从业者提供熟悉的界面和可视化,是模型不可知的,且比替代方法快得多。代码可在该网址获取:this https URL
英文摘要
Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision. We propose ''Rule of Thumb'' (RoT) explanations, a new approach to XAI based upon a novel formulation that identifies the most relevant features for predicting the behaviour of an AI system, for a particular datapoint. We show how RoT is well-suited to enable XAI in: (a) zero-shot classification using large language models (LLMs), (b) auditing of opaque AI systems without model access, and (c) the use of AI in scientific discovery. Additionally, RoT meets specific requirements from leading AI regulations, provides a familiar interface and visualisations for XAI practitioners, is model-agnostic, and is substantially faster than alternatives. Code available at: https://github.com/KaiRawal/Rule-of-Thumb-Explaining-Artificial-Intelligence-Systems-using-Partial-Information
发表机构
- University of Oxford(牛津大学)
- Hasso Plattner Institute(哈索·普拉特纳研究所)
- Weizenbaum Institute(魏茨曼研究所)
机构由 AI 辅助整理,请以论文原文为准。