| Foundational challenges in assuring alignment and safety of large language models U Anwar, A Saparov, J Rando, D Paleka, M Turpin, P Hase, ES Lubana, ... TMLR, 2024 | 465 | 2024 |
| Chain of thought monitorability: A new and fragile opportunity for ai safety T Korbak, M Balesni, E Barnes, Y Bengio, J Benton, J Bloom, M Chen, ... arXiv preprint arXiv:2507.11473, 2025 | 218 | 2025 |
| imitation: Clean imitation learning implementations A Gleave, M Taufeeque, J Rocamonde, E Jenner, SH Wang, S Toyer, ... arXiv preprint arXiv:2211.11972, 2022 | 127 | 2022 |
| When chain of thought is necessary, language models struggle to evade monitors S Emmons, E Jenner, DK Elson, RA Saurous, S Rajamanoharan, H Chen, ... arXiv preprint arXiv:2507.05246, 2025 | 88 | 2025 |
| Chain of thought monitorability: A new and fragile opportunity for ai safety, 2025 T Korbak, M Balesni, E Barnes, Y Bengio, J Benton, J Bloom, M Chen, ... URL https://arxiv. org/abs/2507.11473, 2026 | 56 | 2026 |
| Obfuscated activations bypass LLM latent-space defenses L Bailey, A Serrano, A Sheshadri, M Seleznyov, J Taylor, E Jenner, ... International Conference on Learning Representations 2026, 146838-146882, 2026 | 55 | 2026 |
| Steerable Partial Differential Operators for Equivariant Neural Networks E Jenner, M Weiler ICLR, 2022 | 49 | 2022 |
| Evidence of Learned Look-Ahead in a Chess-Playing Neural Network E Jenner, S Kapur, V Georgiev, C Allen, S Emmons, S Russell NeurIPS, 2024 | 42 | 2024 |
| When Your AI Deceives You: Challenges with Partial Observability of Human Evaluators in Reward Learning L Lang, D Foote, S Russell, A Dragan, E Jenner, S Emmons NeurIPS, 2024 | 34* | 2024 |
| Can reasoning models obfuscate reasoning? stress-testing chain-of-thought monitorability A Zolkowski, W Xing, D Lindner, F Tramèr, E Jenner arXiv preprint arXiv:2510.19851, 2025 | 25 | 2025 |
| others. 2025. Chain of thought monitorability: A new and fragile opportunity for ai safety T Korbak, M Balesni, E Barnes, Y Bengio, J Benton, J Bloom, M Chen, ... Preprint, 22 | 24 | 22 |
| Preprocessing Reward Functions for Interpretability E Jenner, A Gleave NeurIPS Cooperative AI workshop, 2021 | 23 | 2021 |
| STARC: A General Framework For Quantifying Differences Between Reward Functions J Skalse, L Farnik, SR Motwani, E Jenner, A Gleave, A Abate ICLR, 2023 | 21 | 2023 |
| RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors? R Gupta, E Jenner arXiv preprint arXiv:2506.14261, 2025 | 14 | 2025 |
| Diffusion on syntax trees for program synthesis S Kapur, E Jenner, S Russell ICLR, 2025 | 10 | 2025 |
| h’Eigeartaigh U Anwar, A Saparov, J Rando, D Paleka, M Turpin, P Hase, ES Lubana, ... S., Recchia, G., Corsi, G., Chan, A., Anderljung, M., Edwards, L., Petrov, A …, 2024 | 9 | 2024 |
| A general framework for reward function distances E Jenner, JMV Skalse, A Gleave NeurIPS ML Safety Workshop, 2022 | 9 | 2022 |
| Calculus on MDPs: Potential shaping as a gradient E Jenner, H van Hoof, A Gleave arXiv preprint arXiv:2208.09570, 2022 | 8* | 2022 |
| A comparison of causal scrubbing, causal abstractions, and related methods E Jenner, A Garriga-alonso, E Zverev AI Alignment Forum, 2023 | 4 | 2023 |
| Frontier Models Can Take Actions at Low Probabilities A Serrano, W Xing, D Lindner, E Jenner arXiv preprint arXiv:2603.02202, 2026 | 2 | 2026 |
Scott EmmonsGoogle DeepMindVerified email at google.com
