Published in ArXiv, under review at AAAI 2024, 2023
We study the problem of fair sequential decision making given voter preferences.
Recommended citation: Chandak, Nikhil and Goel, Shashwat and Peters, Dominik (2023). "Proportional Aggregation of Preferences for Sequential Decision Making." ArXiv. https://arxiv.org/abs/2306.14858
Published in ACL Repl4NLP Workshop, 2023
We design interpretability experiments to study why Language Models find it difficult to deal with negation
Recommended citation: Singh, Shashwat and Goel, Shashwat and Vaduguru, Saujas and Kumaraguru, Ponnurangam (2023). "Probing Negation in Language Models." ACL Repl4NLP Workshop. http://shash42.github.io/files/negation.pdf
Published in ArXiv, 2023
We study how to evaluate machine unlearning procedures.
Recommended citation: Goel, Shashwat and Prabhu, Ameya and Sanyal Amartya and Lim, Ser-Nam and Torr Philip and Kumaraguru, Ponnurangam (2023). "Towards Adversarial Evaluations for Inexact Machine Unlearning." ArXiv. https://arxiv.org/abs/2201.06640