Alice Xiang

ICLR, 2026 | Zhiteng Li, Lele Chen, Jerone Andrews, Yunhao Ba, Yulun Zhang, Alice Xiang

We propose a generative agent that augments training datasets with synthetic datafor model fine-tuning. Unlike prior work, which uniformly samples synthetic data,our agent iteratively generates relevant samples on-the-fly, aligning with the targetdistribution. It prioritizes...

ACM SIGCHI, 2025 | Morgan Klaus Scheuerman, Dora Zhao*, Jerone T. A. Andrews, Abeba Birhane, Q. Vera Liao*, Georgia Panagiotidou*, Pooja Chitre*, Kathleen Pine, Shawn Walker*, Jieyu Zhao*, Alice Xiang

AI technologies have become ubiquitous, influencing domains from healthcare to finance and permeating our daily lives. Concerns about the values underlying the creation and use of datasets to develop AI technologies are growing. Current dataset practices often disregard crit...

NEURIPS, 2024 | Dora Zhao*, Morgan Klaus Scheuerman, Pooja Chitre*, Jerone Andrews, Georgia Panagiotidou*, Shawn Walker*, Kathleen H. Pine*, Alice Xiang

Despite extensive efforts to create fairer machine learning (ML) datasets, there remains a limited understanding of the practical aspects of dataset curation. Drawing from interviews with 30 ML dataset curators, we present a comprehensive taxonomy of the challenges and trade...

EMNLP, 2024 | Yusuke Hirota, Jerone Andrews, Dora Zhao*, Orestis Papakyriakopoulos*, Apostolos Modas, Yuta Nakashima*, Alice Xiang

We tackle societal bias in image-text datasets by removing spurious correlations between protected groups and image attributes. Traditional methods only target labeled attributes, ignoring biases from unlabeled ones. Using text-guided inpainting models, our approach ensures ...

ECCV, 2024 | Mateo Espinosa Zarlenga*, Swami Sankaranarayanan, Jerone Andrews, Zohreh Shams, Mateja Jamnik*, Alice Xiang

Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously correlated (e.g., “grassy background” and “cows”). Existing bias mitigation methods that aim t...

ICML, 2024 | Dora Zhao*, Jerone T. A. Andrews, Orestis Papakyriakopoulos*, Alice Xiang

Machine learning (ML) datasets, often perceived as neutral, inherently encapsulate abstract and disputed social constructs. Dataset curators frequently employ value-laden terms such as diversity, bias, and quality to characterize datasets. Despite their prevalence, these ter...

FACCT, 2024 | Wiebke Hutiri*, Orestis Papakyriakopoulos*, Alice Xiang

The rapid and wide-scale adoption of AI to generate human speech poses a range of significant ethical and safety risks to society that need to be addressed. For example, a growing number of speech generation incidents are associated with swatting attacks in the United States...

NEURIPS, 2023 | Jerone Andrews, Dora Zhao*, William Thong, Apostolos Modas, Orestis Papakyriakopoulos*, Alice Xiang

Human-centric computer vision (HCCV) data curation practices often neglect privacy and bias concerns, leading to dataset retractions and unfair models. HCCV datasets constructed through nonconsensual web scraping lack crucial metadata for comprehensive fairness and robustnes...

ICCV, 2023 | William Thong, Przemyslaw Joniak*, Alice Xiang

This paper strives to measure apparent skin color in computer vision, beyond a unidimensional scale on skin tone. In their seminal paper Gender Shades, Buolamwini and Gebru have shown how gender classification systems can be biased against women with darker skin tones. While...

AIES, 2023 | Keziah Naggita*, Julienne LaChance, Alice Xiang

Biases in large-scale image datasets are known to influence the performance of computer vision models as a function of geographic context. To investigate the limitations of standard Internet data collection methods in low- and middle-income countries, we analyze human-centri...

ICML, 2023 | Dora Zhao*, Jerone T. A. Andrews, Alice Xiang

As computer vision systems become more widely deployed, there is increasing concern from both the research community and the public that these systems are not only reproducing but amplifying harmful social biases. The phenomenon of bias amplification, which is the focus of t...

FACCT, 2023 | Orestis Papakyriakopoulos*, Anna Seo Gyeong Choi*, William Thong, Dora Zhao*, Jerone Andrews, Rebecca Bourke, Alice Xiang, Allison Koenecke*

Human-centric image datasets are critical to the development of computer vision technologies. However, recent investigations have foregrounded significant ethical issues related to privacy and bias, which have resulted in the complete retraction, or modification, of several ...

ICLR, 2023 | Jerone T. A. Andrews, Przemyslaw Joniak*, Alice Xiang

Few datasets contain self-identified sensitive attributes, inferring attributes risks introducing additional biases, and collecting attributes can carry legal risks. Besides, categorical labels can fail to reflect the continuous nature of human phenotypic diversity, making i...

HARVARD JOURNAL OF LAW & TECHNOLOGY, 2023 | Alice Xiang

The rise of facial recognition and related computer vision technologies has been met with growing anxiety over the potential for artificial intelligence (“AI”) to create mass surveillance systems and further entrench societal biases. These concerns have led to calls for grea...

WSDM, 2023 | Orestis Papakyriakopoulos*, Alice Xiang

Speech AI Technologies are largely trained on publicly available datasets or by the massive web-crawling of speech. In both cases, data acquisition focuses on minimizing collection effort, without necessarily taking the data subjects’ protection or user needs into considerat...

NEURIPS, 2022 | Aida Rahmattalabi, Alice Xiang

Recent interests in causality for fair decision-making systems has been accompanied with great skepticism due to practical and epistemological challenges with applying existing causal fairness approaches. Existing works mainly seek to remove the causal effect of social categ...

NEURIPS, 2022 | Jerone T. A. Andrews, Przemyslaw Joniak*, Alice Xiang

We propose to implicitly learn a set of continuous face-varying dimensions, without ever asking an annotator to explicitly categorize a person. We uncover the dimensions by learning on a novel dataset of 638,180 human judgments of face similarity (FAX). We demonstrate the ut...

NEURIPS, 2022 | Jerone T. A. Andrews, Przemyslaw Joniak*, Alice Xiang

Biases in human-centric computer vision models are often attributed to a lack of sufficient data diversity, with many demographics insufficiently represented. However, auditing datasets for diversity can be difficult, due to an absence of ground-truth labels of relevant feat...

ECCV, 2022 | Jerone T. A. Andrews, Przemyslaw Joniak*, Alice Xiang

Biases in human-centric computer vision models are often attributed to a lack of sufficient data diversity, with many demographics insufficiently represented. However, auditing datasets for diversity can be difficult, due to an absence of ground-truth labels of relevant feat...

EAAMO, 2022 | Jeffrey Brown*, Tina Park*, Jiyoo Chang*, McKane Andrus*, Alice Xiang, Christine Custis*

The effects of AI systems are far-reaching and affect diverse commu- nities all over the world. The demographics of AI teams, however, do not reflect this diversity. Instead, these teams, particularly at big tech companies, are dominated by Western, White, and male work- ers...

TENNESSEE LAW REVIEW, 2021 | Alice Xiang

In recent years, there has been a proliferation of papers in the algorithmic fairness literature proposing various technical definitions of algorithmic bias and methods to mitigate bias. Whether these algorithmic bias mitigation methods would be permissible from a legal pers...

AIES, 2021 | Riccardo Fogliato*, Alice Xiang, Zachary Lipton*, Daniel Nagin*, Alexandra Chouldechova*

The risk of re-offense is considered in decision-making at many stages of the criminal justice system, from pre-trial, to sentencing, to parole. To aid decision makers in their assessments, institutions increasingly rely on algorithmic risk assessment instruments (RAIs). The...

FACCT, 2021 | McKane Andrus*, Elena Spitzer*, Jeffrey Brown*, Alice Xiang

As calls for fair and unbiased algorithmic systems increase, so too does the number of individuals working on algorithmic fairness in industry. However, these practitioners often do not have access to the demographic data they feel they need to detect bias in practice. Even ...