Sledovať
Stephen Casper
Stephen Casper
PhD student, MIT
Overená e-mailová adresa na: mit.edu - Domovská stránka
Názov
Citované v
Citované v
Rok
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
4802023
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
1902023
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, ...
arXiv preprint arXiv:2404.09932, 2024
1352024
Rethinking machine unlearning for large language models
S Liu, Y Yao, J Jia, S Casper, N Baracaldo, P Hase, Y Yao, CY Liu, X Xu, ...
Nature Machine Intelligence, 1-14, 2025
1062025
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
1002023
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
862023
Black-box access is insufficient for rigorous ai audits
S Casper, C Ezell, C Siegmann, N Kolt, TL Curtis, B Bucknall, A Haupt, ...
Proceedings of the 2024 ACM Conference on Fairness, Accountability, and …, 2024
732024
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
432024
Clusterability in neural networks
D Filan, S Casper, S Hod, C Wild, A Critch, S Russell
arXiv preprint arXiv:2103.03386, 2021
352021
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
34*2021
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
332022
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
32*2023
Open problems in technical ai governance
A Reuel, B Bucknall, S Casper, T Fist, L Soder, O Aarne, L Hammond, ...
arXiv preprint arXiv:2407.14981, 2024
272024
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
272023
Latent adversarial training improves robustness to persistent harmful behaviors in llms
A Sheshadri, A Ewart, P Guo, A Lynch, C Wu, V Hebbar, H Sleight, ...
arXiv preprint arXiv:2407.15549, 2024
26*2024
Defending against unforeseen failure modes with latent adversarial training
S Casper, L Schulze, O Patel, D Hadfield-Menell
arXiv preprint arXiv:2403.05030, 2024
262024
The ai risk repository: A comprehensive meta-review, database, and taxonomy of risks from artificial intelligence
P Slattery, AK Saeri, EAC Grundy, J Graham, M Noetel, R Uuk, J Dao, ...
arXiv preprint arXiv:2408.12622, 2024
242024
Multiplex base editing to convert TAG into TAA codons in the human genome
Y Chen, E Hysolli, A Chen, S Casper, S Liu, K Yang, C Liu, G Church
Nature communications 13 (1), 4482, 2022
192022
International Scientific Report on the Safety of Advanced AI (Interim Report)
Y Bengio, S Mindermann, D Privitera, T Besiroglu, R Bommasani, ...
arXiv preprint arXiv:2412.05282, 2024
162024
Probing neural dialog models for conversational understanding
A Saleh, T Deutsch, S Casper, Y Belinkov, S Shieber
arXiv preprint arXiv:2006.08331, 2020
162020
Systém momentálne nemôže vykonať operáciu. Skúste to neskôr.
Články 1–20