Grilling BBQ: The Limits of Bias Benchmarking in LLM Safety Reporting
Nicholas Perello, Przemyslaw A. Grabowicz, Yair Zick. Grilling BBQ: The Limits of Bias Benchmarking in LLM Safety Reporting. Under review, 2026.
Publications
*Equal contribution, ^Equal advising
Under Review
Archival
Discrimination Induced by Algorithmic Recourse Objectives
Nicholas Perello, Cyrus Cousins, Yair Zick, Przemyslaw A. Grabowicz. Discrimination Induced by Algorithmic Recourse Objectives. In ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), 2025. https://doi.org/10.1145/3715275.3732110
Simple Steps to Success: A Method for Step-Based Counterfactual Explanations
JJ (Jenny) Hamer*, Nicholas Perello*, Jake Valladares, Vignesh Viswanathan*, Yair Zick. Simple Steps to Success: A Method for Step-Based Counterfactual Explanations. In Transactions on Machine Learning Research (TMLR), 2024. https://openreview.net/pdf?id=R6ey5DKaoX
Learning from Discriminatory Training Data
Przemyslaw A. Grabowicz*, Nicholas Perello*, and Kenta Takatsu. Learning from Discriminatory Training Data. In AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2023 https://dl.acm.org/doi/10.1145/3600211.3604710
Marrying Fairness and Explainability in Supervised Learning
Przemyslaw A. Grabowicz, Nicholas Perello, and Aarshee Mishra. Marrying Fairness and Explainability in Supervised Learning. In ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), 2022. https://dl.acm.org/doi/10.1145/3531146.3533236
On Optimizing Interventions in Shared Autonomy
Weihao Tan*, David Koleczek*, Siddhant Pradhan*, Nicholas Perello, Vivek Chettiar, Nan Ma, Aaslesha Rajaram, Vishal Rohra, Soundar Srinivasan, H M Sajjad Hossain^, and Yash Chandak^. On Optimizing Interventions in Shared Autonomy. In Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022 https://cdn.aaai.org/ojs/20471/20471-13-24484-1-2-20220628.pdf
Non-Archival
Towards an AI Accountability Policy
Przemyslaw A. Grabowicz, Nicholas Perello, Yair Zick. Towards an AI Accountability Policy. In Comment on FR Doc 2023-07776 Posted by the National Telecommunications and Information Administration, 2023.
Resilience of Supervised Learning Algorithms to Discriminatory Poisoning of Training Data
Przemyslaw A. Grabowicz and Nicholas Perello. Resilience of Supervised Learning Algorithms to Discriminatory Poisoning of Training Data. In 7th International Conference on Computational Social Science (IC2S2), 2021.
Intervention Aware Shared Autonomy
Weihao Tan*, David Koleczek*, Siddhant Pradhan*, Nicholas Perello, Vivek Chettiar, Nan Ma, Aaslesha Rajaram, Vishal Rohra, Soundar Srinivasan, H M Sajjad Hossain^, and Yash Chandak^. Intervention Aware Shared Autonomy. In ICML Workshop on Human-AI Collaboration in Sequential Decision-Making, 2021.
Towards Fair and Explainable Supervised Learning
Aarshee Mishra*, Nicholas Perello*, and Przemyslaw A. Grabowicz. Towards Fair and Explainable Supervised Learning. In ICML Workshop on Socially Responsible Machine Learning (SRML), 2021.