Suivre
Rachel Freedman
Rachel Freedman
UC Berkeley
Adresse e-mail validée de berkeley.edu - Page d'accueil
Titre
Citée par
Citée par
Année
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
4362023
Adapting a kidney exchange algorithm to align with human values
R Freedman, JS Borg, W Sinnott-Armstrong, JP Dickerson, V Conitzer
Artificial Intelligence, 103261, 2020
1342020
Benefits of assistance over reward learning
R Shah, P Freire, N Alex, R Freedman, D Krasheninnikov, L Chan, ...
362020
Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
V Conitzer, R Freedman, J Heitzig, WH Holliday, BM Jacobs, N Lambert, ...
Forty-first International Conference on Machine Learning, 0
23
The expertise problem: Learning from specialized feedback
O Daniels-Koch, R Freedman
arXiv preprint arXiv:2211.06519, 2022
222022
Choice Set Misspecification in Reward Inference
R Freedman, R Shah, A Dragan
The IJCAI-PRICAI-20 Workshop on Artificial Intelligence Safety, 2020
222020
Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
V Conitzer, R Freedman, J Heitzig, WH Holliday, BM Jacobs, N Lambert, ...
arXiv preprint arXiv:2404.10271, 2024
212024
Open problems and fundamental limitations of reinforcement learning from human feedback. arXiv 2023
S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ...
arXiv preprint arXiv:2307.15217, 0
17
Active reward learning from multiple teachers
P Barnett, R Freedman, J Svegliato, S Russell
arXiv preprint arXiv:2303.00894, 2023
152023
Open problems and fundamental limitations of reinforcement learning from human feedback. CoRR, abs/2307.15217, 2023. doi: 10.48550
S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ...
arXiv preprint ARXIV.2307.15217, 0
15
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback (arXiv: 2307.15217). arXiv
S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ...
82023
Active teacher selection for reinforcement learning from human feedback
R Freedman, J Svegliato, K Wray, S Russell
arXiv preprint arXiv:2310.15288, 2023
72023
& Hadfield-Menell, D.(2023). 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, 0
7
Linear Probe Penalties Reduce LLM Sycophancy
H Papadatos, R Freedman
arXiv preprint arXiv:2412.00967, 2024
2024
Aligning with Heterogeneous Preferences for Kidney Exchange
R Freedman
arXiv preprint arXiv:2006.09519, 2020
2020
Adapting a Kidney Exchange Algorithm to Incorporate Human Values
R Freedman
Duke University, 2017
2017
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–16