Jan Leike - RankMe

84 papers A* 11A 8B 5Journal 54Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks. CoRR Hoagy Cunningham, Jerry Wei, Zihan Wang, Andrew Persic, Alwin Peng, Jordan Abderrachid, Raj Agarwal, Bobby Chen, Austin Cohen, Andy Dau, Alek Dimitriev, Rob Gilson, Logan Howard, Yijin Hua, Jared Kaplan, Jan Leike, Mu Lin, Christopher Liu, Vladimir Mikulik, Rohit Mittapalli, Clare O'Hara, Jin Pan, Nikhil Saxena, Alex Silverstein, Yue Song, Xunjie Yu, Giulio Zhou, Ethan Perez, Mrinank Sharma
2026	J	`jnl`	Excess Description Length of Learning Generalizable Predictors. CoRR Elizabeth Donoway, Hailey Joren, Fabien Roger, Jan Leike
2025	J	`jnl`	Auditing language models for hidden objectives. CoRR Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey, Jonathan Marcus, Siddharth Mishra-Sharma, Daniel M. Ziegler, Emmanuel Ameisen, Joshua Batson, Tim Belonax, Samuel R. Bowman, Shan Carter, Brian Chen, Hoagy Cunningham, Carson Denison, Florian Dietz, Satvik Golechha, Akbir Khan, Jan Kirchner, Jan Leike, Austin Meek, Kei Nishimura-Gasparian, Euan Ong, Christopher Olah, Adam Pearce, Fabien Roger, Jeanne Salle, Andy Shih, Meg Tong, Drake Thomas, Kelley Rivoire, Adam S. Jermyn, Monte MacDiarmid, Tom Henighan, Evan Hubinger
2025	J	`jnl`	Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming. CoRR Mrinank Sharma, Meg Tong, Jesse Mu, Jerry Wei, Jorrit Kruthoff, Scott Goodfriend, Euan Ong, Alwin Peng, Raj Agarwal, Cem Anil, Amanda Askell, Nathan Bailey, Joe Benton, Emma Bluemke, Samuel R. Bowman, Eric Christiansen, Hoagy Cunningham, Andy Dau, Anjali Gopal, Rob Gilson, Logan Graham, Logan Howard, Nimit Kalra, Taesung Lee, Kevin Lin, Peter Lofgren, Francesco Mosconi, Clare O'Hara, Catherine Olsson, Linda Petrini, Samir Rajani, Nikhil Saxena, Alex Silverstein, Tanya Singh, Theodore R. Sumers, Leonard Tang, Kevin K. Troy, Constantin Weisser, Ruiqi Zhong, Giulio Zhou, Jan Leike, Jared Kaplan, Ethan Perez
2025	J	`jnl`	Forecasting Rare Language Model Behaviors. CoRR Erik Jones, Meg Tong, Jesse Mu, Mohammed Mahfoud, Jan Leike, Roger B. Grosse, Jared Kaplan, William Fithian, Ethan Perez, Mrinank Sharma
2025	J	`jnl`	Limit-Computable Grains of Truth for Arbitrary Computable Extensive-Form (Un)Known Games. CoRR Cole Wyeth, Marcus Hutter, Jan Leike, Jessica Taylor
2025	J	`jnl`	Natural Emergent Misalignment from Reward Hacking in Production RL. CoRR Monte MacDiarmid, Benjamin Wright, Jonathan Uesato, Joe Benton, Jonathan Kutasov, Sara Price, Naia Bouscal, Samuel R. Bowman, Trenton Bricken, Alex Cloud, Carson Denison, Johannes Gasteiger, Ryan Greenblatt, Jan Leike, Jack Lindsey, Vladimir Mikulik, Ethan Perez, Alex Rodrigues, Drake Thomas, Albert Webson, Daniel M. Ziegler, Evan Hubinger
2025	J	`jnl`	Reasoning Models Don't Always Say What They Think. CoRR Yanda Chen, Joe Benton, Ansh Radhakrishnan, Jonathan Uesato, Carson Denison, John Schulman, Arushi Somani, Peter Hase, Misha Wagner, Fabien Roger, Vladimir Mikulik, Samuel R. Bowman, Jan Leike, Jared Kaplan, Ethan Perez
2025	A*	`conf`	Scaling and evaluating sparse autoencoders. ICLR Leo Gao, Tom Dupré la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford, Ilya Sutskever, Jan Leike, Jeffrey Wu
2025	J	`jnl`	Unsupervised Elicitation of Language Models. CoRR Jiaxin Wen, Zachary Ankner, Arushi Somani, Peter Hase, Samuel Marks, Jacob Goldman-Wetzler, Linda Petrini, Henry Sleight, Collin Burns, He He, Shi Feng, Ethan Perez, Jan Leike
2024	J	`jnl`	LLM Critics Help Catch LLM Bugs. CoRR Nat McAleese, Rai Michael Pokorny, Juan Felipe Ceron Uribe, Evgenia Nitishinskaya, Maja Trebacz, Jan Leike
2024	A*	`conf`	Let's Verify Step by Step. ICLR Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, Karl Cobbe
2024	J	`jnl`	Prover-Verifier Games improve legibility of LLM outputs. CoRR Jan Hendrik Kirchner, Yining Chen, Harri Edwards, Jan Leike, Nat McAleese, Yuri Burda
2024	J	`jnl`	Scaling and evaluating sparse autoencoders. CoRR Leo Gao, Tom Dupré la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford, Ilya Sutskever, Jan Leike, Jeffrey Wu
2024	A*	`conf`	Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision. ICML Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, Jeffrey Wu
2023	J	`jnl`	Let's Verify Step by Step. CoRR Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, Karl Cobbe
2023	J	`jnl`	Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision. CoRR Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, Jeff Wu
2022	J	`jnl`	Safe Deep RL in 3D Environments using Human Feedback. CoRR Matthew Rahtz, Vikrant Varma, Ramana Kumar, Zachary Kenton, Shane Legg, Jan Leike
2022	J	`jnl`	Self-critiquing models for assisting human evaluators. CoRR William Saunders, Catherine Yeh, Jeff Wu, Steven Bills, Long Ouyang, Jonathan Ward, Jan Leike
2022	A*	`conf`	Training language models to follow instructions with human feedback. NeurIPS Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F. Christiano, Jan Leike, Ryan Lowe
2022	J	`jnl`	Training language models to follow instructions with human feedback. CoRR Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F. Christiano, Jan Leike, Ryan Lowe
2021	J	`jnl`	Evaluating Large Language Models Trained on Code. CoRR Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Pondé de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mikhail Pavlov, Alethea Power, Lukasz Kaiser, Mohammad Bavarian, Clemens Winter, Philippe Tillet, Felipe Petroski Such, Dave Cummings, Matthias Plappert, Fotios Chantzis, Elizabeth Barnes, Ariel Herbert-Voss, William Hebgen Guss, Alex Nichol, Alex Paino, Nikolas Tezak, Jie Tang, Igor Babuschkin, Suchir Balaji, Shantanu Jain, William Saunders, Christopher Hesse, Andrew N. Carr, Jan Leike, Joshua Achiam, Vedant Misra, Evan Morikawa, Alec Radford, Matthew Knight, Miles Brundage, Mira Murati, Katie Mayer, Peter Welinder, Bob McGrew, Dario Amodei, Sam McCandlish, Ilya Sutskever, Wojciech Zaremba
2021	J	`jnl`	Institutionalising Ethics in AI through Broader Impact Requirements. CoRR Carina E. A. Prunkl, Carolyn Ashurst, Markus Anderljung, Helena Webb, Jan Leike, Allan Dafoe
2021	J	`jnl`	Institutionalizing ethics in AI through broader impact requirements. Nat. Mach. Intell. Carina E. A. Prunkl, Carolyn Ashurst, Markus Anderljung, Helena Webb, Jan Leike, Allan Dafoe
2021	A*	`conf`	Quantifying Differences in Reward Functions. ICLR Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell, Jan Leike
2021	J	`jnl`	Recursively Summarizing Books with Human Feedback. CoRR Jeff Wu, Long Ouyang, Daniel M. Ziegler, Nisan Stiennon, Ryan Lowe, Jan Leike, Paul F. Christiano
2020	J	`jnl`	Active Reinforcement Learning: Observing Rewards at a Cost. CoRR David Krueger, Jan Leike, Owain Evans, John Salvatier
2020	J	`jnl`	Hidden Incentives for Auto-Induced Distributional Shift. CoRR David Krueger, Tegan Maharaj, Jan Leike
2020	A*	`conf`	Learning Human Objectives by Evaluating Hypothetical Behavior. ICML Siddharth Reddy, Anca D. Dragan, Sergey Levine, Shane Legg, Jan Leike
2020	A*	`conf`	Pitfalls of Learning a Reward Function Online. IJCAI Stuart Armstrong, Jan Leike, Laurent Orseau, Shane Legg
2020	J	`jnl`	Pitfalls of learning a reward function online. CoRR Stuart Armstrong, Jan Leike, Laurent Orseau, Shane Legg
2020	J	`jnl`	Quantifying Differences in Reward Functions. CoRR Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell, Jan Leike
2019	J	`jnl`	Learning Human Objectives by Evaluating Hypothetical Behavior. CoRR Siddharth Reddy, Anca D. Dragan, Sergey Levine, Shane Legg, Jan Leike
2019	—	`conf`	Learning to Understand Goal Specifications by Modelling Reward. ICLR (Poster) Dzmitry Bahdanau, Felix Hill, Jan Leike, Edward Hughes, Seyed Arian Hosseini, Pushmeet Kohli, Edward Grefenstette
2018	—	`conf`	Geometric Nontermination Arguments. TACAS (2) Jan Leike, Matthias Heizmann
2018	—	`conf`	Jointly Learning "What" and "How" from Instructions and Goal-States. ICLR (Workshop) Dzmitry Bahdanau, Felix Hill, Jan Leike, Edward Hughes, Pushmeet Kohli, Edward Grefenstette
2018	J	`jnl`	Learning to Follow Language Instructions with Adversarial Reward Induction. CoRR Dzmitry Bahdanau, Felix Hill, Jan Leike, Edward Hughes, Pushmeet Kohli, Edward Grefenstette
2018	J	`jnl`	On the computability of Solomonoff induction and AIXI. Theor. Comput. Sci. Jan Leike, Marcus Hutter
2018	A*	`conf`	Reward learning from human preferences and demonstrations in Atari. NeurIPS Borja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, Dario Amodei
2018	J	`jnl`	Reward learning from human preferences and demonstrations in Atari. CoRR Borja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, Dario Amodei
2018	J	`jnl`	Scalable agent alignment via reward modeling: a research direction. CoRR Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, Shane Legg
2018	J	`jnl`	Scaling shared model governance via model splitting. CoRR Miljan Martic, Jan Leike, Andrew Trask, Matteo Hessel, Shane Legg, Pushmeet Kohli
2017	J	`jnl`	AI Safety Gridworlds. CoRR Jan Leike, Miljan Martic, Victoria Krakovna, Pedro A. Ortega, Tom Everitt, Andrew Lefrancq, Laurent Orseau, Shane Legg
2017	—	`conf`	Deep Reinforcement Learning from Human Preferences. NIPS Paul F. Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, Dario Amodei
2017	J	`jnl`	Deep reinforcement learning from human preferences. CoRR Paul F. Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, Dario Amodei
2017	A	`conf`	Generalised Discount Functions applied to a Monte-Carlo AI u Implementation. AAMAS Sean Lamont, John Aslanides, Jan Leike, Marcus Hutter
2017	J	`jnl`	Generalised Discount Functions applied to a Monte-Carlo AImu Implementation. CoRR Sean Lamont, John Aslanides, Jan Leike, Marcus Hutter
2017	A*	`conf`	On Thompson Sampling and Asymptotic Optimality. IJCAI Jan Leike, Tor Lattimore, Laurent Orseau, Marcus Hutter
2017	A*	`conf`	Universal Reinforcement Learning Algorithms: Survey and Experiments. IJCAI John Aslanides, Jan Leike, Marcus Hutter
2017	J	`jnl`	Universal Reinforcement Learning Algorithms: Survey and Experiments. CoRR John Aslanides, Jan Leike, Marcus Hutter
2016	A	`conf`	A Formal Solution to the Grain of Truth Problem. UAI Jan Leike, Jessica Taylor, Benya Fallenstein
2016	J	`jnl`	A Formal Solution to the Grain of Truth Problem. CoRR Jan Leike, Jessica Taylor, Benya Fallenstein
2016	J	`jnl`	Exploration Potential. CoRR Jan Leike
2016	J	`jnl`	Geometric Nontermination Arguments. CoRR Jan Leike, Matthias Heizmann
2016	A	`conf`	Loss Bounds and Time Complexity for Speed Priors. AISTATS Daniel Filan, Jan Leike, Marcus Hutter
2016	J	`jnl`	Loss Bounds and Time Complexity for Speed Priors. CoRR Daniel Filan, Marcus Hutter, Jan Leike
2016	J	`jnl`	Nonparametric General Reinforcement Learning. CoRR Jan Leike
2016	A	`conf`	Thompson Sampling is Asymptotically Optimal in General Environments. UAI Jan Leike, Tor Lattimore, Laurent Orseau, Marcus Hutter
2016	J	`jnl`	Thompson Sampling is Asymptotically Optimal in General Environments. CoRR Jan Leike, Tor Lattimore, Laurent Orseau, Marcus Hutter
2016	A	`conf`	Ultimate Automizer with Two-track Proofs - (Competition Contribution). TACAS Matthias Heizmann, Daniel Dietsch, Marius Greitschus, Jan Leike, Betim Musa, Claus Schätzle, Andreas Podelski
2015	—	`conf`	A Definition of Happiness for Reinforcement Learning Agents. AGI Mayank Daswani, Jan Leike
2015	J	`jnl`	A Definition of Happiness for Reinforcement Learning Agents. CoRR Mayank Daswani, Jan Leike
2015	A*	`conf`	Bad Universal Priors and Notions of Optimality. COLT Jan Leike, Marcus Hutter
2015	J	`jnl`	Bad Universal Priors and Notions of Optimality. CoRR Jan Leike, Marcus Hutter
2015	A	`conf`	On the Computability of AIXI. UAI Jan Leike, Marcus Hutter
2015	J	`jnl`	On the Computability of AIXI. CoRR Jan Leike, Marcus Hutter
2015	B	`conf`	On the Computability of Solomonoff Induction and Knowledge-Seeking. ALT Jan Leike, Marcus Hutter
2015	J	`jnl`	On the Computability of Solomonoff Induction and Knowledge-Seeking. CoRR Jan Leike, Marcus Hutter
2015	J	`jnl`	Ranking Templates for Linear Loops. Log. Methods Comput. Sci. Jan Leike, Matthias Heizmann
2015	—	`conf`	Sequential Extensions of Causal and Evidential Decision Theory. ADT Tom Everitt, Jan Leike, Marcus Hutter
2015	J	`jnl`	Sequential Extensions of Causal and Evidential Decision Theory. CoRR Tom Everitt, Jan Leike, Marcus Hutter
2015	B	`conf`	Solomonoff Induction Violates Nicod's Criterion. ALT Jan Leike, Marcus Hutter
2015	J	`jnl`	Solomonoff Induction Violates Nicod's Criterion. CoRR Jan Leike, Marcus Hutter
2015	A	`conf`	Ultimate Automizer with Array Interpolation - (Competition Contribution). TACAS Matthias Heizmann, Daniel Dietsch, Jan Leike, Betim Musa, Andreas Podelski
2014	J	`jnl`	Geometric Series as Nontermination Arguments for Linear Lasso Programs. CoRR Jan Leike, Matthias Heizmann
2014	B	`conf`	Indefinitely Oscillating Martingales. ALT Jan Leike, Marcus Hutter
2014	J	`jnl`	Indefinitely Oscillating Martingales. CoRR Jan Leike, Marcus Hutter
2014	J	`jnl`	Linear Ranking for Linear Lasso Programs. CoRR Matthias Heizmann, Jochen Hoenicke, Jan Leike, Andreas Podelski
2014	J	`jnl`	Ranking Function Synthesis for Linear Lasso Programs. CoRR Jan Leike
2014	A	`conf`	Ranking Templates for Linear Loops. TACAS Jan Leike, Matthias Heizmann
2014	J	`jnl`	Ranking Templates for Linear Loops. CoRR Jan Leike, Matthias Heizmann
2014	B	`conf`	Synthesis for Polynomial Lasso Programs. VMCAI Jan Leike, Ashish Tiwari
2013	B	`conf`	Linear Ranking for Linear Lasso Programs. ATVA Matthias Heizmann, Jochen Hoenicke, Jan Leike, Andreas Podelski
2013	J	`jnl`	Synthesis for Polynomial Lasso Programs. CoRR Jan Leike, Ashish Tiwari