| Training a helpful and harmless assistant with reinforcement learning from human feedback Y Bai, A Jones, K Ndousse, A Askell, A Chen, N DasSarma, D Drain, ... arXiv preprint arXiv:2204.05862, 2022 | 948 | 2022 |
| Constitutional ai: Harmlessness from ai feedback Y Bai, S Kadavath, S Kundu, A Askell, J Kernion, A Jones, A Chen, ... arXiv preprint arXiv:2212.08073, 2022 | 747 | 2022 |
| A general language assistant as a laboratory for alignment A Askell, Y Bai, A Chen, D Drain, D Ganguli, T Henighan, A Jones, ... arXiv preprint arXiv:2112.00861, 2021 | 328* | 2021 |
| Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned D Ganguli, L Lovitt, J Kernion, A Askell, Y Bai, S Kadavath, B Mann, ... arXiv preprint arXiv:2209.07858, 2022 | 290 | 2022 |
| In-context learning and induction heads C Olsson, N Elhage, N Nanda, N Joseph, N DasSarma, T Henighan, ... arXiv preprint arXiv:2209.11895, 2022 | 246* | 2022 |
| A mathematical framework for transformer circuits N Elhage, N Nanda, C Olsson, T Henighan, N Joseph, B Mann, A Askell, ... Transformer Circuits Thread 1 (1), 12, 2021 | 229* | 2021 |
| Predictability and surprise in large generative models D Ganguli, D Hernandez, L Lovitt, A Askell, Y Bai, A Chen, T Conerly, ... Proceedings of the 2022 ACM Conference on Fairness, Accountability, and …, 2022 | 219 | 2022 |
| Discovering language model behaviors with model-written evaluations E Perez, S Ringer, K Lukošiūtė, K Nguyen, E Chen, S Heiner, C Pettit, ... arXiv preprint arXiv:2212.09251, 2022 | 161 | 2022 |
| The capacity for moral self-correction in large language models D Ganguli, A Askell, N Schiefer, TI Liao, K Lukošiūtė, A Chen, A Goldie, ... arXiv preprint arXiv:2302.07459, 2023 | 112 | 2023 |
| Language models (mostly) know what they know S Kadavath, T Conerly, A Askell, T Henighan, D Drain, E Perez, ... arXiv preprint arXiv:2207.05221, 2022 | 104 | 2022 |
| Emergent social learning via multi-agent reinforcement learning KK Ndousse, D Eck, S Levine, N Jaques International conference on machine learning, 7991-8004, 2021 | 69* | 2021 |
| Towards understanding sycophancy in language models M Sharma, M Tong, T Korbak, D Duvenaud, A Askell, SR Bowman, ... arXiv preprint arXiv:2310.13548, 2023 | 67 | 2023 |
| Evolution through large models J Lehman, J Gordon, S Jain, K Ndousse, C Yeh, KO Stanley Handbook of Evolutionary Machine Learning, 331-366, 2023 | 60 | 2023 |
| Measuring progress on scalable oversight for large language models SR Bowman, J Hyun, E Perez, E Chen, C Pettit, S Heiner, K Lukošiūtė, ... arXiv preprint arXiv:2211.03540, 2022 | 58 | 2022 |
| Baryons and baryonic matter in the large and heavy quark limits TD Cohen, N Kumar, KK Ndousse Physical Review C—Nuclear Physics 84 (1), 015204, 2011 | 29 | 2011 |
| Sleeper agents: Training deceptive llms that persist through safety training E Hubinger, C Denison, J Mu, M Lambert, M Tong, M MacDiarmid, ... arXiv preprint arXiv:2401.05566, 2024 | 24 | 2024 |
| Specific versus general principles for constitutional ai S Kundu, Y Bai, S Kadavath, A Askell, A Callahan, A Chen, A Goldie, ... arXiv preprint arXiv:2310.13798, 2023 | 12 | 2023 |
