| 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 | 1144 | 2022 |
| Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ... arXiv preprint arXiv:2206.04615, 2022 | 1000 | 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 | 908 | 2022 |
| 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 | 348 | 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 | 311 | 2021 |
| Scattering forms and the positive geometry of kinematics, color and the worldsheet N Arkani-Hamed, Y Bai, S He, G Yan Journal of High Energy Physics 2018 (5), 1-78, 2018 | 296 | 2018 |
| In-context learning and induction heads C Olsson, N Elhage, N Nanda, N Joseph, N DasSarma, T Henighan, ... arXiv preprint arXiv:2209.11895, 2022 | 263 | 2022 |
| Predictability and surprise in large generative models D Ganguli, D Hernandez, L Lovitt, N DasSarma, T Henighan, A Jones, ... arXiv preprint arXiv:2202.07785, 2022 | 250 | 2022 |
| Positive geometries and canonical forms N Arkani-Hamed, Y Bai, T Lam Journal of High Energy Physics 2017 (11), 39, 2017 | 234 | 2017 |
| A mathematical framework for transformer circuits N Elhage, N Nanda, C Olsson, T Henighan, N Joseph, B Mann, A Askell, ... Transformer Circuits Thread, 2021 | 228 | 2021 |
| 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 | 187 | 2022 |
| 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 | 130 | 2022 |
| The capacity for moral self-correction in large language models D Ganguli, A Askell, N Schiefer, T Liao, K Lukošiūtė, A Chen, A Goldie, ... arXiv preprint arXiv:2302.07459, 2023 | 124 | 2023 |
| Gravitational-wave physics with Cosmic Explorer: limits to low-frequency sensitivity ED Hall, K Kuns, JR Smith, Y Bai, C Wipf, S Biscans, RX Adhikari, K Arai, ... Physical Review D 103 (12), 122004, 2021 | 78 | 2021 |
| Measuring Progress on Scalable Oversight for Large Language Models SR Bowman, J Hyun, E Perez, E Chen, C Pettit, S Heiner, K Lukosuite, ... arXiv preprint arXiv:2211.03540, 2022 | 73 | 2022 |
| The amplituhedron from momentum twistor diagrams Y Bai, S He Journal of High Energy Physics 2015 (2), 65, 2015 | 70 | 2015 |
| A mathematical framework for transformer circuits. Transformer Circuits Thread, 2021 N Elhage, N Nanda, C Olsson, T Henighan, N Joseph, B Mann, A Askell, ... | 59 | |
| The amplituhedron and the one-loop Grassmannian measure Y Bai, S He, T Lam Journal of High Energy Physics 2016 (1), 112, 2016 | 51 | 2016 |
| Phase-sensitive optomechanical amplifier for quantum noise reduction in laser interferometers Y Bai, G Venugopalan, K Kuns, C Wipf, A Markowitz, AR Wade, Y Chen, ... Physical Review A 102 (2), 023507, 2020 | 13 | 2020 |
| Positive Geometry of the S-Matrix Y Bai Princeton, NJ: Princeton University, 2018 | 1 | 2018 |
