Artificial intelligence systems, especially those using machine learning, are being deployed in domains from hiring to loan issuance in order to automate these complex decisions. Judging both the effectiveness and fairness of these AI systems, and their human decision making counterpart, is a complex and important topic studied across both computational and social sciences. Within machine learning, a common way to address bias in downstream classifiers is to resample the training data to offset disparities. For example, if hiring rates vary by some protected class, then one may equalize the rate within the training set to alleviate bias in the resulting classifier. While simple and seemingly effective, these methods have typically only been evaluated using data obtained through convenience samples, introducing selection bias and label bias into metrics. Within the social sciences, psychology, public health, and medicine, audit studies, in which fictitious ``testers'' (e.g., resumes, emails, patient actors) are sent to subjects (e.g., job openings, businesses, doctors) in randomized control trials, provide high quality data that support rigorous estimates of discrimination. In this paper, we investigate how data from audit studies can be used to improve our ability to both train and evaluate automated hiring algorithms. We find that such data reveals cases where the common fairness intervention method of equalizing base rates across classes appears to achieve parity using traditional measures, but in fact has roughly 10% disparity when measured appropriately. We additionally introduce interventions based on individual treatment effect estimation methods that further reduce algorithmic discrimination using this data.
AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach
University of Washington(华盛顿大学);University of Washington - Bothell(华盛顿大学博塞尔校区);UC Berkeley(加州大学伯克利分校);Amazon(亚马逊公司);Stanford University(斯坦福大学);Amazon GenAI(亚马逊生成式AI部门)
Learning About Algorithm Auditing in Five Steps: Scaffolding How High School Youth Can Systematically and Critically Evaluate Machine Learning Applications
University of Pennsylvania(宾夕法尼亚大学);Teachers College, Columbia University(哥伦比亚大学教师学院)
Oxford Internet Institute, University of Oxford(牛津大学牛津互联网研究院);Digital Ethics Center, Yale University(耶鲁大学数字伦理中心);Harvard Law School(哈佛大学法学院);Center for Information Technology Policy, Princeton University(普林斯顿大学信息技术政策中心)
Technion - Israel Institute of Technology(以色列理工学院);ALTER (Association for Long Term Existence and Resilience)(ALTER(长期存在与韧性协会));Transformative Futures Institute(变革性未来研究所);National Intelligence University(国家情报大学)
Auditing Data Membership in Reinforcement Learning With Verifiable Rewards
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Shanghai Jiao Tong University(上海交通大学);Shandong University(山东大学);Xidian University(西安电子科技大学);Wuhan University(武汉大学)
Compliant But Unsatisfactory: The Gap Between Auditing Standards and Practices for Probabilistic Genotyping Software
University of California, Berkeley(加州大学伯克利分校);Wright State University(莱特州立大学);Forensic Bioinformatic Services, Inc.(法医生物信息学服务公司);ELLIS Institute(ELLIS研究所);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
Auditing large language models: a three-layered approach
University of Oxford(牛津大学);Princeton University(普林斯顿大学);Centre for the Governance of AI(人工智能治理中心);Goethe University Frankfurt(法兰克福歌德大学);University of Bologna(博洛尼亚大学)
Governing AI Forgetting: Auditing for Machine Unlearning Compliance
School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society, The Chinese University of Hong Kong, Shenzhen, China(科学与工程学院,深圳人工智能与机器人社会研究所,香港中文大学(深圳));Data Science and Analytics Thrust, Information Hub, Hong Kong University of Science and Technology (Guangzhou), China(数据科学与分析方向,信息中心,香港科学与技术大学(广州));Internet of Things Thrust, Information Hub, Hong Kong University of Science and Technology (Guangzhou), China(物联网方向,信息中心,香港科学与技术大学(广州))
Get Your Workload in Order: Game Theoretic Prioritization of Database Auditing
Department of Electrical Engineering and Computer Science, Vanderbilt University(范德堡大学电气工程与计算机科学系);Department of Electrical Engineering and Computer Science, University of California, Berkeley(加利福尼亚大学伯克利分校电气工程与计算机科学系);Department of Computer Science, University of Houston(休斯顿大学计算机科学系);Department of Biomedical Informatics, Vanderbilt University(范德堡大学生物医学信息学系)