activity
20192022
most citedBOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation

208 citations · 219 across the 6 of their papers we have counts for

collaborators

7 papers

cs.LG20224 cited

Rethinking Stability for Attribution-based Explanations

Chirag Agarwal, Nari Johnson, Martin Pawelczyk +4

As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are st…

cs.CL20212 cited

Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification

Yada Pruksachatkun, Satyapriya Krishna, Jwala Dhamala +2

Existing bias mitigation methods to reduce disparities in model outcomes across cohorts have focused on data augmentation, debiasing model embeddings, or adding fairness-based opti…

cs.LG2021

Grounding Complex Navigational Instructions Using Scene Graphs

Michiel de Jong, Satyapriya Krishna, Anuva Agarwal

Training a reinforcement learning agent to carry out natural language instructions is limited by the available supervision, i.e. knowing when the instruction has been carried out.…

cs.CR2021

ADePT: Auto-encoder based Differentially Private Text Transformation

Satyapriya Krishna, Rahul Gupta, Christophe Dupuy

Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used…

cs.CL2021208 cited

BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation

Jwala Dhamala, Tony Sun, Varun Kumar +4

Recent advances in deep learning techniques have enabled machines to generate cohesive open-ended text when prompted with a sequence of words as context. While these models now emp…

cs.LG20201 cited

Towards classification parity across cohorts

Aarsh Patel, Rahul Gupta, Mukund Harakere +3

Recently, there has been a lot of interest in ensuring algorithmic fairness in machine learning where the central question is how to prevent sensitive information (e.g. knowledge a…