@inproceedings{lang2024whenyourais,
    title={When Your {AI}s Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback},
    author={Lang, Leon and Foote, Davis and Russell, Stuart and Dragan, Anca and Jenner, Erik and Emmons, Scott},
    booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
    year={2024}
}