AI Safety

Glenn Matlin, Isaac Song, Anthony Wen-Ming Zang, and Mark O. Riedl
No One Wins in Nuclear War: Social Simulations of High-Stakes Military Decision-Making
Proceedings of the COLM 2026 Workshop on Social Simulations with LLMs (2026).
arXiv Workshop bibtexSocial Simulation Agents Large Language Models AI Safety

Mark O. Riedl and Glenn Matlin
Position: AI is Not Ready for Strategic Conflict
Proceedings of the COLM 2026 Workshop on Social Simulations with LLMs (2026).
Workshop bibtexSocial Simulation Agents Policy and Law AI Safety

Geigh Zollicoffer, Tanush Chopra, Mingkuan Yan, Xiaoxu Ma, Kenneth Eaton, and Mark Riedl
World Model Robustness via Surprise Recognition
Proceedings of the 2026 CVPR Findings (2026).
arXiv Conference bibtexAgents Reinforcement Learning AI Safety

Glenn Matlin, Parv Mahajan, Isaac Song, Yixiong Hao, Ryan Bard, Stu Topp, Evan Montoya, M. Rehan Parwani, Soham Shetty, and Mark Riedl
Shall We Play a Game? Language Models for Open-ended Wargames
Proceedings of the 2025 EMNLP Word Play Workshop (2025).
arXiv Workshop bibtexSocial Simulation Agents AI Safety

Geigh Zollicoffer, Kenneth Eaton, Jonathan Balloch, Julia Kim, Riedl Mark O., and Robert Wright
Novelty Detection in Reinforcement Learning with World Models
International Conference on Machine Learning (2025).
arXiv Conference bibtexAgents Reinforcement Learning AI Safety

Ashutosh Baheti, Ximing Lu, Faeze Brahman, Ronan Le Bras, Maarten Sap, and Mark O. Riedl
Improving Language Models with Advantage-based Offline Policy Gradients
Proceedings of ICLR 2024 (2024).
arXiv Conference bibtexLarge Language Models Reinforcement Learning Value Alignment AI Safety

Ashutosh Baheti, Maarten Sap, Alan Ritter, and Mark O. Riedl
Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts
Proceedings of EMNLP 2021 (2021).
arXiv Conference bibtexLarge Language Models Value Alignment AI Safety

Md Sultan Al Nahian, Spencer Frazier, Brent Harrison, and Mark O. Riedl
Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior
arXiv:2104.09469 (2021).
arXiv bibtexAgents Reinforcement Learning Value Alignment AI Safety

Xiangyu Peng, S. Li, Spencer Frazier, and Mark O. Riedl
Reducing Non-Normative Text Generation from Language Models
International Conference on Natural Language Generation (2020).
arXiv Conference bibtexLarge Language Models Value Alignment AI Safety

Mark O. Riedl and Brent. Harrison
Enter the Matrix: A Virtual World Approach to Safely Interruptable Autonomous Systems
Proceedings of the AAAI 2017 Workshop on SafeAI (2017).
arXiv Workshop bibtexAgents Reinforcement Learning AI Safety

Mark Riedl and Brent Harrison
Using Stories to Teach Human Values to Artificial Agents
Proceedings of the 2nd International Workshop on AI, Ethics and Society (2016).
PDF Workshop bibtexAgents Value Alignment AI Safety

Brent Harrsion and Mark O Riedl
Learning From Stories: Using Crowdsourced Narratives to Train Virtual Agents
Proceedings of the 2016 AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (2016).
PDF Conference bibtexAgents Value Alignment AI Safety Human Computation

Brent Harrison and Mark Riedl
Towards Learning From Stories: An Approach for Interactive Machine Learning
Proceedings of the AAAI'16 Workshop on Symbiotic Cognitive Systems (2016).
PDF Workshop bibtexAgents Value Alignment AI Safety

Brent Harrison, Siddhartha Banerjee, and Mark O. Riedl
Learning from Stories: Using Natural Communication to Train Believable Agents
Proceedings of the 2016 IJCAI Workshop on Interactive Machine Learning (2016).
PDF Workshop bibtexAgents Value Alignment AI Safety