Scheming AIs: Will AIs fake alignment during training in order to get power?

14 November 2023

Papers citing "Scheming AIs: Will AIs fake alignment during training in order to get power?"

18 / 18 papers shown

Title
Ctrl-Z: Controlling AI Agents via Resampling Aryan Bhatt Cody Rushing Adam Kaufman Tyler Tracy Vasil Georgiev David Matolcsi Akbir Khan B. S. AAML 30 1 0 14 Apr 2025
How to evaluate control measures for LLM agents? A trajectory from today to superintelligence Tomek Korbak Mikita Balesni Buck Shlegeris Geoffrey Irving ELM 27 1 0 07 Apr 2025
Safety Guardrails for LLM-Enabled Robots Zachary Ravichandran Alexander Robey Vijay R. Kumar George Pappas Hamed Hassani 61 2 0 10 Mar 2025
A sketch of an AI control safety case Tomek Korbak Joshua Clymer Benjamin Hilton Buck Shlegeris Geoffrey Irving 80 5 0 28 Jan 2025
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models Cameron Tice Philipp Alexander Kreer Nathan Helm-Burger Prithviraj Singh Shahani Fedor Ryzhenkov Jacob Haimes Felix Hofstätter Teun van der Weij 82 1 0 02 Dec 2024
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats Jiaxin Wen Vivek Hebbar Caleb Larson Aryan Bhatt Ansh Radhakrishnan ... Shi Feng He He Ethan Perez Buck Shlegeris Akbir Khan AAML 81 8 0 26 Nov 2024
$The Two-Hop Curse: LLMs trained on A$\rightarrow$B, B$\rightarrow$C fail to learn A$\rightarrow$C$ The Two-Hop Curse: LLMs trained on A $\rightarrow$ B, B $\rightarrow$ C fail to learn A $\rightarrow$ C Mikita Balesni Tomek Korbak Owain Evans ReLM LRM 81 0 0 25 Nov 2024
Safety case template for frontier AI: A cyber inability argument Arthur Goemans Marie Davidsen Buhl Jonas Schuett Tomek Korbak Jessica Wang Benjamin Hilton Geoffrey Irving 58 15 0 12 Nov 2024
Towards evaluations-based safety cases for AI scheming Mikita Balesni Marius Hobbhahn David Lindner Alexander Meinke Tomek Korbak ... Dan Braun Bilal Chughtai Owain Evans Daniel Kokotajlo Lucius Bushnaq ELM 47 9 0 29 Oct 2024
Looking Inward: Language Models Can Learn About Themselves by Introspection Felix J Binder James Chua Tomek Korbak Henry Sleight John Hughes Robert Long Ethan Perez Miles Turpin Owain Evans KELM AIFin LRM 35 12 0 17 Oct 2024
On scalable oversight with weak LLMs judging strong LLMs Zachary Kenton Noah Y. Siegel János Kramár Jonah Brown-Cohen Samuel Albanie ... Rishabh Agarwal David Lindner Yunhao Tang Noah D. Goodman Rohin Shah ELM 43 29 0 05 Jul 2024
Identifying the Source of Generation for Large Language Models Bumjin Park Jaesik Choi 29 0 0 05 Jul 2024
AI Sandbagging: Language Models can Strategically Underperform on Evaluations Teun van der Weij Felix Hofstätter Ollie Jaffe Samuel F. Brown Francis Rhys Ward ELM 47 23 0 11 Jun 2024
Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals Joshua Clymer Caden Juang Severin Field CVBM 34 1 0 08 May 2024
Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant Olli Järviniemi Evan Hubinger 34 12 0 25 Apr 2024
Universal Neurons in GPT2 Language Models Wes Gurnee Theo Horsley Zifan Carl Guo Tara Rezaei Kheirkhah Qinyi Sun Will Hathaway Neel Nanda Dimitris Bertsimas MILM 102 37 0 22 Jan 2024
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision Collin Burns Pavel Izmailov Jan Hendrik Kirchner Bowen Baker Leo Gao ... Adrien Ecoffet Manas Joglekar Jan Leike Ilya Sutskever Jeff Wu ELM 50 258 0 14 Dec 2023
AI Control: Improving Safety Despite Intentional Subversion Ryan Greenblatt Buck Shlegeris Kshitij Sachan Fabien Roger 31 40 0 12 Dec 2023