Obserwuj
Erik Jones
Erik Jones
UC Berkeley
Zweryfikowany adres z berkeley.edu
Tytuł
Cytowane przez
Cytowane przez
Rok
Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet
N Bien, P Rajpurkar, RL Ball, J Irvin, A Park, E Jones, M Bereket, BN Patel, ...
PLoS medicine 15 (11), e1002699, 2018
7032018
Impact of a deep learning assistant on the histopathologic classification of liver cancer
A Kiani, B Uyumazturk, P Rajpurkar, A Wang, R Gao, E Jones, Y Yu, ...
NPJ digital medicine 3 (1), 23, 2020
2582020
Automatically Auditing Large Language Models via Discrete Optimization
E Jones, A Dragan, A Raghunathan, J Steinhardt
International Conference on Machine Learning, 15307-15329, 2023
1502023
Orca 2: Teaching small language models how to reason
A Mitra, L Del Corro, S Mahajan, A Codas, C Simoes, S Agarwal, X Chen, ...
arXiv preprint arXiv:2311.11045, 2023
1402023
Robust Encodings: A Framework for Combating Adversarial Typos
E Jones, R Jia*, A Raghunathan*, P Liang
Proceedings of the 58th Annual Meeting of the Association for Computational …, 2020
1232020
Capturing Failures of Large Language Models via Human Cognitive Biases
E Jones, J Steinhardt
Advances in Neural Information Processing Systems 35, 11785-11799, 2022
982022
Selective Classification Can Magnify Disparities Across Groups
E Jones*, S Sagawa*, PW Koh*, A Kumar, P Liang
International Conference on Learning Representations (ICLR), 2021
602021
Mass-Producing Failures of Multimodal Systems with Language Models
S Tong*, E Jones*, J Steinhardt
arXiv preprint arXiv:2306.12105, 2023
382023
Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
M Yuksekgonul, V Chandrasekaran, E Jones, S Gunasekar, R Naik, ...
arXiv preprint arXiv:2309.15098, 2023
332023
Teaching Language Models to Hallucinate Less with Synthetic Tasks
E Jones, H Palangi, C Simões, V Chandrasekaran, S Mukherjee, A Mitra, ...
arXiv preprint arXiv:2310.06827, 2023
262023
Feedback Loops With Language Models Drive In-Context Reward Hacking
A Pan, E Jones, M Jagadeesan, J Steinhardt
arXiv preprint arXiv:2402.06627, 2024
192024
Deep Learning for the Digital Pathologic Diagnosis of Cholangiocarcinoma and Hepatocellular Carcinoma: Evaluating the Impact of a Web-based Diagnostic Assistant
B Uyumazturk, A Kiani, P Rajpurkar, A Wang, RL Ball, R Gao, Y Yu, ...
arXiv preprint arXiv:1911.07372, 2019
182019
Adversaries Can Misuse Combinations of Safe Models
E Jones, A Dragan, J Steinhardt
arXiv preprint arXiv:2406.14595, 2024
32024
Best-of-N Jailbreaking
J Hughes, S Price, A Lynch, R Schaeffer, F Barez, S Koyejo, H Sleight, ...
arXiv preprint arXiv:2412.03556, 2024
22024
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–14