通过生成挑战样本，找出AI决策与人类判断的差异。
Exploring the Lands Between: A Method for Finding Differences between AI-Decisions and Human Ratings through Generated Samples
- 在生成模型潜空间中寻找挑战性样本，对比AI与人类判断
- 收集11,200条人类评分数据，揭示人脸模型偏差
- 适合评估AI公平性及跨群体表现的科研人员
日常生活中许多重要决策，如生物特征认证，均由人工智能系统做出。这些系统可能与人类预期存在偏差，仅在现有清晰数据上测试不足以发现此类问题。本文提出一种方法，在生成模型的潜空间中寻找对决策模型而言具有挑战性的样本，使其难以匹配人类期望。将这些样本同时呈现给决策模型与人类评分者，可识别出模型决策与人类直觉一致或矛盾的区域。该方法应用于人脸识别模型，并基于100名参与者收集了11,200条人类评分数据。我们分析了数据结果，探讨该方法如何用于探索AI模型在不同情境和用户群体中的表现。
原文摘要 · Abstract (English)
Many important decisions in our everyday lives, such as authentication via biometric models, are made by Artificial Intelligence (AI) systems. These can be in poor alignment with human expectations, and testing them on clear-cut existing data may not be enough to uncover those cases. We propose a method to find samples in the latent space of a generative model, designed to be challenging for a decision-making model with regard to matching human expectations. By presenting those samples to both the decision-making model and human raters, we can identify areas where its decisions align with human intuition and where they contradict it. We apply this method to a face recognition model and collect a dataset of 11,200 human ratings from 100 participants. We discuss findings from our dataset and how our approach can be used to explore the performance of AI models in different contexts and for different user groups.
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。