| Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks P Lewis, E Perez, A Piktus, F Petroni, V Karpukhin, N Goyal, H Küttler, ... NeurIPS 2020, 2020 | 12554 | 2020 |
| FiLM: Visual Reasoning with a General Conditioning Layer E Perez, F Strub, H De Vries, V Dumoulin, A Courville AAAI 2018, 2018 | 3116* | 2018 |
| 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 | 2223 | 2022 |
| Red teaming language models with language models E Perez, S Huang, F Song, T Cai, R Ring, J Aslanides, A Glaese, ... EMNLP 2022, 2022 | 921 | 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 | 788 | 2022 |
| ELI5: Long Form Question Answering A Fan, Y Jernite*, E Perez*, D Grangier, J Weston, M Auli Association for Computational Linguistics (ACL) 2019, 2019 | 756 | 2019 |
| Language models don't always say what they think: Unfaithful explanations in chain-of-thought prompting M Turpin, J Michael, E Perez, S Bowman Advances in Neural Information Processing Systems 36, 74952-74965, 2023 | 661 | 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 | 605 | 2022 |
| True Few-Shot Learning with Language Models E Perez, D Kiela, K Cho NeurIPS 2021, 2021 | 555 | 2021 |
| Discovering language model behaviors with model-written evaluations E Perez, S Ringer, K Lukosiute, K Nguyen, E Chen, S Heiner, C Pettit, ... Findings of the association for computational linguistics: ACL 2023, 13387-13434, 2023 | 485 | 2023 |
| Towards understanding sycophancy in language models M Sharma, M Tong, T Korbak, D Duvenaud, A Askell, SR Bowman, ... ICLR, 2023 | 470 | 2023 |
| Supervised multimodal bitransformers for classifying images and text D Kiela, S Bhooshan, H Firooz, E Perez, D Testuggine arXiv preprint arXiv:1909.02950, 2019 | 365 | 2019 |
| Pretraining language models with human preferences T Korbak, K Shi, A Chen, R Bhalerao, CL Buckley, J Phang, SR Bowman, ... ICML 2023, 2023 | 263 | 2023 |
| 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 | 257 | 2024 |
| Feature-wise transformations V Dumoulin, E Perez, N Schucher, F Strub, H Vries, A Courville, Y Bengio Distill 3 (7), e11, 2018 | 245* | 2018 |
| Studying large language model generalization with influence functions R Grosse, J Bae, C Anil, N Elhage, A Tamkin, A Tajdini, B Steiner, D Li, ... arXiv preprint arXiv:2308.03296, 2023 | 232 | 2023 |
| Measuring faithfulness in chain-of-thought reasoning T Lanham, A Chen, A Radhakrishnan, B Steiner, C Denison, ... arXiv preprint arXiv:2307.13702, 2023 | 225 | 2023 |
| Many-shot jailbreaking C Anil, E Durmus, N Panickssery, M Sharma, J Benton, S Kundu, J Batson, ... Advances in Neural Information Processing Systems 37, 129696-129742, 2024 | 213 | 2024 |
| 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 | 212 | 2023 |
| Unsupervised Question Decomposition for Question Answering E Perez, P Lewis, W Yih, K Cho, D Kiela EMNLP 2020, 2020 | 201 | 2020 |
Douwe KielaContextual AI, Stanford UniversityVerified email at stanford.edu
