Search Results for author:
Found 14 papers, 2 papers with code
Ranking Large Language Models without Ground Truth
and a set of LLMs, we rank them without access to any ground truth or reference responses.
SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models
Current datasets for unwanted social bias auditing are limited to studying protected demographic features such as race and gender.
Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions
In this paper, focusing specifically on compositions of functions arising from the different pillars, we aim to reduce this gap, develop new insights for trustworthy ML, and answer questions such as the following.
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
Interpretable and explainable machine learning has seen a recent surge of interest.
Anomaly Attribution with Likelihood Compensation
In either case, one would ideally want to compute a ``responsibility score'' indicative of the extent to which an input variable is responsible for the anomalous output.
Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model Recommendations
In this study, we investigate the level of implicit race information available to ML models and human experts and the implications of model-detectable differences in clinical notes.
Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets
The use of machine learning (ML)-based language models (LMs) to monitor content online is on the rise.
An Empirical Study of Accuracy, Fairness, Explainability, Distributional Robustness, and Adversarial Robustness
To ensure trust in AI models, it is becoming increasingly apparent that evaluation of models must be extended beyond traditional performance metrics, like accuracy, to other dimensions, such as fairness, explainability, adversarial robustness, and distribution shift.
AI Explainability 360: Impact and Design
As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations.
Your fairness may vary: Pretrained language model fairness in toxic text classification
Through the analysis of more than a dozen pretrained language models of varying sizes on two toxic text classification tasks (English), we demonstrate that focusing on accuracy measures alone can lead to models with wide variation in fairness characteristics.
Understanding racial bias in health using the Medical Expenditure Panel Survey data
Over the years, several studies have demonstrated that there exist significant disparities in health indicators in the United States population across various groups.
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability.
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking.
Interpretable Multi-Objective Reinforcement Learning through Policy Orchestration
To ensure that agents behave in ways aligned with the values of the societies in which they operate, we must develop techniques that allow these agents to not only maximize their reward in an environment, but also to learn and follow the implicit constraints of society.
Multi-Objective Reinforcement Learning
reinforcement-learning
