7 citations · 8 across the 7 of their papers we have counts for
7 papers
Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization
Ayan Majumdar, Shounak Paul, Pushpdeep Singh +6
The growing complexity of content moderation policies presents a critical challenge for their consistent operationalization. While foundation models possess the basic capabilities…
Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms
Pushpdeep Singh, Sayeh Jarollahi, Ayan Majumdar +5
Empirical research on content moderation is fundamentally constrained by the opaque deployment of moderation systems on major social media platforms. To this end, the recent emerge…
From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recourse
Lena Marie Budde, Ayan Majumdar, Richard Uth +2
Algorithmic recourse aims to provide actionable recommendations that enable individuals to change unfavorable model outcomes, and prior work has extensively studied properties such…
Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study
Ayan Majumdar, Feihao Chen, Jinghui Li +1
Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a regulatory need for data auditing…
A Causal Framework to Measure and Mitigate Non-binary Treatment Discrimination
Ayan Majumdar, Deborah D. Kanubala, Kavya Gupta +1
Fairness studies of algorithmic decision-making systems often simplify complex decision processes, such as bail or loan approvals, into binary classification tasks. However, these…
Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Making
Miriam Rateike, Ayan Majumdar, Olga Mineeva +2
Decision making algorithms, in practice, are often trained on data that exhibits a variety of biases. Decision-makers often aim to take decisions based on some ground-truth target…
Do Invariances in Deep Neural Networks Align with Human Perception?
Vedant Nanda, Ayan Majumdar, Camila Kolling +4
An evaluation criterion for safe and trustworthy deep learning is how well the invariances captured by representations of deep neural networks (DNNs) are shared with humans. We ide…