Search Results for author:
Found 27 papers, 5 papers with code
Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation
We pose two central questions: (1) To what extent do prompts with explicit gender references reflect gender differences in opinion in the United States on topics of social relevance?
A Critical Survey on Fairness Benefits of XAI
In this critical survey, we analyze typical claims on the relationship between explainable AI (XAI) and fairness to disentangle the multidimensional relationship between these two concepts.
Mitigating Label Bias via Decoupled Confident Learning
While the presence of labeling bias has been discussed conceptually, there is a lack of methodologies to address this problem.
Human-Centered Responsible Artificial Intelligence: Current & Future Trends
In recent years, the CHI community has seen significant growth in research on Human-Centered Responsible Artificial Intelligence.
Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection
We propose framing toxicity detection as multi-task learning (MTL), allowing a model to specialize on the relationships that are relevant to each demographic group while also leveraging shared properties across groups.
Learning Complementary Policies for Human-AI Teams
We then extend our approach to leverage opportunities and mitigate risks that arise in important contexts in practice: 1) when a team is composed of multiple humans with differential and potentially complementary abilities, 2) when the observational data includes consistent deterministic actions, and 3) when the covariate distribution of future decisions differ from that in the historical data.
Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
In this work, we study the effects of feature-based explanations on distributive fairness of AI-assisted decisions, specifically focusing on the task of predicting occupations from short textual bios.
Imputation Strategies Under Clinical Presence: Impact on Algorithmic Fairness
Machine learning risks reinforcing biases present in data, and, as we argue in this work, in what is absent from data.
Toward Supporting Perceptual Complementarity in Human-AI Collaboration via Reflection on Unobservables
Our findings indicate that presenting prompts about unobservables can change how humans integrate model outputs and unobservables, but do not necessarily lead to improved performance.
Algorithmic Fairness in Business Analytics: Directions for Research and Practice
The extensive adoption of business analytics (BA) has brought financial gains and increased efficiencies.
More Data Can Lead Us Astray: Active Data Acquisition in the Presence of Label Bias
We then empirically show that, when overlooking label bias, collecting more data can aggravate bias, and imposing fairness constraints that rely on the observed labels in the data collection process may not address the problem.
Doubting AI Predictions: Influence-Driven Second Opinion Recommendation
Effective human-AI collaboration requires a system design that provides humans with meaningful ways to make sense of and critically evaluate algorithmic recommendations.
Justice in Misinformation Detection Systems: An Analysis of Algorithms, Stakeholders, and Potential Harms
Faced with the scale and surge of misinformation on social media, many platforms and fact-checking organizations have turned to algorithms for automating key parts of misinformation detection pipelines.
On the Relationship Between Explanations, Fairness Perceptions, and Decisions
It is known that recommendations of AI-based systems can be incorrect or unfair.
Social Norm Bias: Residual Harms of Fairness-Aware Algorithms
Many modern machine learning algorithms mitigate bias by enforcing fairness constraints across coarsely-defined groups related to a sensitive attribute like gender or race.
The effect of differential victim crime reporting on predictive policing systems
Our analysis is based on a simulation patterned after district-level victimization and crime reporting survey data for Bogot\'a, Colombia.
Leveraging Expert Consistency to Improve Algorithmic Decision Support
However, there is frequently a gap between decision objectives and what is captured in the observed outcomes used as labels to train ML models.
Killings of social leaders in the Colombian post-conflict: Data analysis for investigative journalism
After the peace agreement of 2016 with FARC, the killings of social leaders have emerged as an important post-conflict challenge for Colombia.
Applications Computers and Society
What's in a Name? Reducing Bias in Bios without Access to Protected Attributes
In the context of mitigating bias in occupation classification, we propose a method for discouraging correlation between the predicted probability of an individual's true occupation and a word embedding of their name.
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives.
Proceedings of NeurIPS 2018 Workshop on Machine Learning for the Developing World: Achieving Sustainable Impact
This is the Proceedings of NeurIPS 2018 Workshop on Machine Learning for the Developing World: Achieving Sustainable Impact, held in Montreal, Canada on December 8, 2018
What are the biases in my word embedding?
The inputs to our algorithm are a list of target tokens, e. g. names, and a word embedding.
Learning under selective labels in the presence of expert consistency
We explore the problem of learning under selective labels in the context of algorithm-assisted decision making.
Proceedings of NIPS 2017 Workshop on Machine Learning for the Developing World
This is the Proceedings of NIPS 2017 Workshop on Machine Learning for the Developing World, held in Long Beach, California, USA on December 8, 2017
Canonical Autocorrelation Analysis
We present an extension of sparse Canonical Correlation Analysis (CCA) designed for finding multiple-to-multiple linear correlations within a single set of variables.
Lass-0: sparse non-convex regression by local search
We compute approximate solutions to L0 regularized linear regression using L1 regularization, also known as the Lasso, as an initialization step.
