用局部信息快速解释AI决策，无需模型访问
Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information
- 基于关键特征识别，通过部分输入推断AI行为
- 零样本分类、模型审计、科学发现场景均适用
- 无需模型权限，速度快且符合监管要求
可解释人工智能（XAI）旨在揭示人工智能系统如何做出特定决策。我们提出一种名为“经验法则”（Rule of Thumb, RoT）的新方法，基于一种新颖的公式化框架，识别出针对特定数据点预测AI系统行为最相关的特征。我们证明了RoT在以下场景中非常适用：(a) 使用大型语言模型进行零样本分类，(b) 在无模型访问权限的情况下审计黑箱AI系统，以及 (c) 在科学发现中使用AI。此外，RoT满足主流人工智能法规的具体要求，为XAI从业者提供熟悉的操作界面与可视化方式，具有模型无关性，并显著快于现有方法。代码已公开于：https://github.com/KaiRawal/Rule-of-Thumb-Explaining-Artificial-Intelligence-Systems-using-Partial-Information
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。