paper-with-me

홈 › Papers

Who Decides if AI is Fair? The Labels Problem in Algorithmic Auditing

2021-11-16 · Abhilash Mishra, Yash Gorana

Labelled "ground truth" datasets are routinely used to evaluate and audit AI algorithms applied in high-stakes settings. However, there do not exist widely accepted benchmarks for the quality of labels in these datasets. We provide empirical evidence that quality of labels can significantly distort the results of algorithmic audits in real-world settings. Using data annotators typically hired by AI firms in India, we show that fidelity of the ground truth data can lead to spurious differences in performance of ASRs between urban and rural populations. After a rigorous, albeit expensive, label cleaning process, these disparities between groups disappear. Our findings highlight how trade-offs between label quality and data annotation costs can complicate algorithmic audits in practice. They also emphasize the need for development of consensus-driven, widely accepted benchmarks for label quality.

📄 PDF Abstract BibTeX arXiv:2111.08723

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Peer-induced Fairness: A Causal Approach for Algorithmic Fairness Auditing

2024-08-05 · Shiqi Fang, Zexun Chen, Jake Ansell

With the European Union's Artificial Intelligence Act taking effect on 1 August 2024, high-risk AI applications must adhere to stringent transparency and fairness standards. This paper addresses a crucial question: how c…

Causal InferencecounterfactualDecision MakingFairness

Assessing Classifier Fairness with Collider Bias

2020-10-08 · Zhenlong Xu, Jixue Liu, Debo Cheng, Jiuyong Li 외

The increasing application of machine learning techniques in everyday decision-making processes has brought concerns about the fairness of algorithmic decision-making. This paper concerns the problem of collider bias whi…

Decision MakingFairness

Auditing LLMs for Algorithmic Fairness in Casenote-Augmented Tabular Prediction

2026-04-21 · Xiao Qi Lee, Ezinne Nwankwo, Angela Zhou arxiv

LLMs are increasingly being considered for prediction tasks in high-stakes social service settings, but their algorithmic fairness properties in this context are poorly understood. In this short technical report, we audi…

Multi-class Classification

Mathematical Framework for Online Social Media Auditing

2022-09-12 · Wasim Huleihel, Yehonathan Refael

Social media platforms (SMPs) leverage algorithmic filtering (AF) as a means of selecting the content that constitutes a user's feed with the aim of maximizing their rewards. Selectively choosing the contents to be shown…

Decision Making

Auditing and Enforcing Conditional Fairness via Optimal Transport

2024-10-17 · Mohsen Ghassemi, Alan Mishler, Niccolo Dalmasso, Luhao Zhang 외

Conditional demographic parity (CDP) is a measure of the demographic parity of a predictive model or decision process when conditioning on an additional feature or set of features. Many algorithmic fairness techniques ex…

Fairness