Publications

Papers

• Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems

  By Parand A. Alamdari, Toryn Q. Klassen, and Sheila A. McIlraith

  In FAccT-26: ACM Conference on Fairness, Accountability, and Transparency, 2026.

  [ Paper ]
• Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data

  By Andrew Li, Toryn Q. Klassen, Andrew Wang, Parand A. Alamdari, and Sheila A. McIlraith

  In NeurIPS-25: Proceedings of the 39th Annual Conference on Neural Information Processing Systems, 2025.

  [ Paper ]
• Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems

  By Parand A. Alamdari, Toryn Q. Klassen, and Sheila A. McIlraith

  In ICML R2FM-25: ICML 2025 Workshop on Reliable and Responsible Foundation Models.

  [ Paper ]
• Pluralistic Alignment Over Time

  By Toryn Q. Klassen, Parand A. Alamdari, and Sheila A. McIlraith

  In NeurIPS PA-24: NeurIPS Workshop on Pluralistic Alignment, 2024.

  [ Paper ]
• Being Considerate as a Pathway to Pluralistic Alignment for Agentic AI

  By Parand A. Alamdari, Toryn Q. Klassen, Rodrigo Toro Icarte, and Sheila A. McIlraith

  In NeurIPS PA-24: NeurIPS Workshop on Pluralistic Alignment, 2024.

  [ Paper ]
• Policy Aggregation

  By Parand A. Alamdari, Soroush Ebadian, and Ariel Procaccia

  In NeurIPS-24: Proceedings of the Thirty-Eighth Annual Conference on Neural Information Processing Systems, 2024.

  [ Paper ]
• Jump Starting Bandits with LLM-Generated Prior Knowledge

  By Parand A. Alamdari, Yanshuai Cao, and Kevin Wilson

  In EMNLP-24: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024.

  [ Paper ]
• Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making

  By Parand A. Alamdari, Toryn Q. Klassen, Elliot Creager, and Sheila A. McIlraith

  In ICML-24: Proceedings of the 41st International Conference on Machine Learning, 2024

  [ Paper ]
• Remembering to Be Fair: On Non-Markovian Fairness in Sequential Decision Making (Preliminary Report)

  By Parand A. Alamdari, Toryn Q. Klassen, Elliot Creager, and Sheila A. McIlraith

  In NeurIPS AFT-23: NeurIPS Workshop on Algorithmic Fairness through the Lens of Time, 2023.

  [ Paper ]
• Epistemic Side Effects: An AI Safety Problem

  By Toryn Q. Klassen, Parand A. Alamdari, and Sheila A. McIlraith

  In AAMAS-23: Proceedings of the 22st International Conference on Autonomous Agents and Multiagent Systems, 2023.

  [ Paper | Code | Poster ]
• Epistemic Side Effects & Avoiding Them (Sometimes)

  By Toryn Q. Klassen, Parand A. Alamdari, and Sheila A. McIlraith

  In NeurIPS MLSafety-22: NeurIPS Workshop on Machine Learning Safety, 2022.

  [ Paper | Code | Poster ]
• Be Considerate: Avoiding Negative Side Effects in Reinforcement Learning

  By Parand A. Alamdari, Toryn Q. Klassen, Rodrigo Toro Icarte, and Sheila A. McIlraith

  In AAMAS-22: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, 2022.

  [ Paper | Code ]
• Avoiding Negative Side Effects by Considering Others

  By Parand A. Alamdari, Toryn Q. Klassen, Rodrigo Toro Icarte, and Sheila A. McIlraith

  In NeurIPS SafeRL-21: NeurIPS Workshop on Safe and Robust Control of Uncertain Systems, 2021.

  [ Paper | Code | Poster ]
• Formal Methods with a Touch of Magic

  By Parand A. Alamdari, Guy Avni, Anna Lukina, and Thomas A. Henzinger

  In FMCAD-20: In Proceedings of the 20th Conference on Formal Methods in Computer-Aided Design, 2020.

  [ Paper ]