Robert MC Carthy, Joey Skaf, Luis Ibañez-Lissen, Vasil Georgiev, Connor Watts, Hannes Whittingham, Lorena González-Manzano, Cameron Tice, Edward James Young, Puria Radmard, David Lindner. Large language models can learn and generalize steganographic chain-of-thought under process supervision. In Danielle Belgrave, Cheng Zhang 0005, Laura N. Montoya, Hsuan-Tien Lin, Razvan Pascanu, Piotr Koniusz, Marzyeh Ghassemi, Nancy Chen, Iván Vladimir Meza Ruíz, Arturo Loaiza-Bonilla, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diago, CA, USA, December 2-7, 2025 / Mexico City, Mexico, November 30 - December 5, 2025. 2025. [doi]
Abstract is missing.