Keyword

deceptive alignment

Description: A proposed AI safety failure in which an artificial intelligence system conceals misaligned objectives while appearing to follow its training or instructions.
Wikidata ID: wiki/Q139147598
OpenAlex ID: keywords/deceptive-alignment
2022 · Ngo, Richard, Chan, Lawrence, et al. · arXiv (Cornell University) · 472
2023 · Carlsmith, Joe · arXiv (Cornell University) · 161
2025 · Schoen, Bronson, Nitishinskaya, Evgenia, et al. · arXiv (Cornell University) · 153
2025 · Chua, James, Betley, Jan, et al. · arXiv (Cornell University) · 83
2025 · Ji, Jiaming, Chen, Wenqi, et al. · arXiv (Cornell University) · 47
2025 · Zolkowski, Artur, Xing, Wen, et al. · arXiv (Cornell University) · 31
2023 · Carranza, Andres, Pai, Dhruv, et al. · arXiv (Cornell University) · 26
2025 · Chaudhary, Maheep, Su, Ian, et al. · arXiv (Cornell University) · 21
2026 · Taufeeque, Mohammad, Heimersheim, Stefan, et al. · arXiv (Cornell University) · 17
2025 · Saikat Barua, Mostafizur Rahman, et al. · Research Square · 16
2025 · Krishna, Satyapriya, Zou, Andy, et al. · arXiv (Cornell University) · 15
2025 · J. Koorndijk · Proceedings of the AAAI Symposium Series · 13
2026 · Bengio, Yoshua, Richardson, Oliver, et al. · arXiv (Cornell University) · 10
2026 · Parmar, Manoj · arXiv (Cornell University) · 9
2020 · Holtman, Koen · arXiv (Cornell University) · 9
2025 · Nell Watson · Oxford University Press eBooks · 8
2020 · Koen Holtman · Lecture notes in computer science · 8
2024 · Fronsdal, Kai, Lindner, David · arXiv (Cornell University) · 5
2026 · Tingjiang Wei, Qin Ni, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 4
2024 · Hewson, Joshua T. S. · arXiv (Cornell University) · 4
2020 · Miller, James D., Yampolskiy, Roman, et al. · arXiv (Cornell University) · 4
2026 · Pallakonda, Bhanu, Hindsbo, Mikkel, et al. · arXiv (Cornell University) · 3
2026 · Naing, Htet Ko Ko · Zenodo (CERN European Organization for Nuclear Research) · 2
Works count: 193
Citation count: 1,152
Year
Topic
Type