Search Results for author:
Found 14 papers, 5 papers with code
REAL ML: Recognizing, Exploring, and Articulating Limitations of Machine Learning Research
Transparency around limitations can improve the scientific rigor of research, help ensure appropriate interpretation of research findings, and make research claims more credible.
Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices
How are algorithmic assessments built, validated, and examined for bias?
Language (Technology) is Power: A Critical Survey of "Bias" in NLP
We survey 146 papers analyzing "bias" in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyzing "bias" is an inherently normative process.
Language (Technology) is Power: A Critical Survey of ``Bias'' in NLP
We survey 146 papers analyzing {``}bias{''} in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyzing {``}bias{''} is an inherently normative process.
Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs
Disaggregated evaluations of AI systems, in which system performance is assessed and reported separately for different groups of people, are conceptually simple.
Computer Vision and Conflicting Values: Describing People with Automated Alt Text
In this paper, we investigate the ethical dilemmas faced by companies that have adopted the use of computer vision for producing alt text: textual descriptions of images for blind and low vision people, We use Facebook's automatic alt text tool as our primary case study.
An Uncommon Task: Participatory Design in Legal AI
Despite growing calls for participation in AI design, there are to date few empirical studies of what these processes look like and how they can be structured for meaningful engagement with domain experts.
Measuring Representational Harms in Image Captioning
We propose multiple measurement techniques for each type of harm.
Mimetic Models: Ethical Implications of AI that Acts Like You
An emerging theme in artificial intelligence research is the creation of models to simulate the decisions and behavior of specific people, in domains including game-playing, text generation, and artistic expression.
Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification.
Informational Diversity and Affinity Bias in Team Growth Dynamics
Prior work has provided strong evidence that, within organizational settings, teams that bring a diversity of information and perspectives to a task are more effective than teams that do not.
Multi-Target Multiplicity: Flexibility and Fairness in Target Specification under Resource Constraints
Along the way, we refine the study of single-target multiplicity by introducing notions of multiplicity that respect resource constraints -- a feature of many real-world tasks that is not captured by existing notions of predictive multiplicity.
On the Actionability of Outcome Prediction
Through a simple model encompassing actions, latent states, and measurements, we demonstrate that pure outcome prediction rarely results in the most effective policy for taking actions, even when combined with other measurements.
Measuring machine learning harms from stereotypes: requires understanding who is being harmed by which errors in what ways
However, certain stereotype-violating errors are more experientially harmful for men, potentially due to perceived threats to masculinity.
