| Open problems and fundamental limitations of reinforcement learning from human feedback S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ... arXiv preprint arXiv:2307.15217, 2023 | 150 | 2023 |
| Toward transparent ai: A survey on interpreting the inner structures of deep neural networks T Räuker, A Ho, S Casper, D Hadfield-Menell 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 464-483, 2023 | 103* | 2023 |
| Explore, establish, exploit: Red teaming language models from scratch S Casper, J Lin, J Kwon, G Culp, D Hadfield-Menell arXiv preprint arXiv:2306.09442, 2023 | 41 | 2023 |
| Clusterability in neural networks D Filan, S Casper, S Hod, C Wild, A Critch, S Russell arXiv preprint arXiv:2103.03386, 2021 | 32 | 2021 |
| Frivolous units: Wider networks are not really that wide S Casper, X Boix, V D'Amario, L Guo, M Schrimpf, K Vinken, G Kreiman Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 6921-6929, 2021 | 28* | 2021 |
| Scalable and transferable black-box jailbreaks for language models via persona modulation R Shah, S Pour, A Tagade, S Casper, J Rando arXiv preprint arXiv:2311.03348, 2023 | 25 | 2023 |
| Robust feature-level adversaries are interpretability tools S Casper, M Nadeau, D Hadfield-Menell, G Kreiman Advances in Neural Information Processing Systems 35, 33093-33106, 2022 | 23 | 2022 |
| Red teaming deep neural networks with feature synthesis tools S Casper, T Bu, Y Li, J Li, K Zhang, K Hariharan, D Hadfield-Menell Advances in Neural Information Processing Systems 36, 80470-80516, 2023 | 18* | 2023 |
| Probing neural dialog models for conversational understanding A Saleh, T Deutsch, S Casper, Y Belinkov, S Shieber arXiv preprint arXiv:2006.08331, 2020 | 16 | 2020 |
| Rethinking Machine Unlearning for Large Language Models S Liu, Y Yao, J Jia, S Casper, N Baracaldo, P Hase, X Xu, Y Yao, H Li, ... arXiv preprint arXiv:2402.08787, 2024 | 10 | 2024 |
| Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness? K Liu, S Casper, D Hadfield-Menell, J Andreas arXiv preprint arXiv:2312.03729, 2023 | 10 | 2023 |
| Diagnostics for deep neural networks with automated copy/paste attacks S Casper, K Hariharan, D Hadfield-Menell arXiv preprint arXiv:2211.10024, 2022 | 9 | 2022 |
| Quantifying local specialization in deep neural networks S Hod, D Filan, S Casper, A Critch, S Russell arXiv preprint arXiv:2110.08058, 2021 | 9 | 2021 |
| Graphical clusterability and local specialization in deep neural networks S Casper, S Hod, D Filan, C Wild, A Critch, S Russell ICLR 2022 Workshop on PAIR {\textasciicircum} 2Struct: Privacy …, 2022 | 8 | 2022 |
| Detecting modularity in deep neural networks S Hod, S Casper, D Filan, C Wild, A Critch, S Russell | 7 | 2021 |
| Black-Box Access is Insufficient for Rigorous AI Audits S Casper, C Ezell, C Siegmann, N Kolt, TL Curtis, B Bucknall, A Haupt, ... arXiv preprint arXiv:2401.14446, 2024 | 6 | 2024 |
| Eight Methods to Evaluate Robust Unlearning in LLMs A Lynch, P Guo, A Ewart, S Casper, D Hadfield-Menell arXiv preprint arXiv:2402.16835, 2024 | 4 | 2024 |
| Measuring the success of diffusion models at imitating human artists S Casper, Z Guo, S Mogulothu, Z Marinov, C Deshpande, RJ Yew, Z Dai, ... arXiv preprint arXiv:2307.04028, 2023 | 4 | 2023 |
| Red Teaming with Mind Reading: White-Box Adversarial Policies Against RL Agents S Casper, T Killian, G Kreiman, D Hadfield-Menell arXiv preprint arXiv:2209.02167, 2022 | 4* | 2022 |
| Achilles heels for agi/asi via decision theoretic adversaries S Casper arXiv preprint arXiv:2010.05418, 2020 | 4 | 2020 |
Dylan Hadfield-MenellMassachusetts Institute of TechnologyVerified email at csail.mit.edu
