Author of the publication

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

S. Casper, X. Davies, C. Shi, T. Gilbert, J. Scheurer, J. Rando, R. Freedman, T. Korbak, D. Lindner, P. Freire, T. Wang, S. Marks, C. Ségerie, M. Carroll, A. Peng, P. Christoffersen, M. Damani, S. Slocum, U. Anwar, A. Siththaranjan, M. Nadeau, E. Michaud, J. Pfau, D. Krasheninnikov, X. Chen, L. Langosco, P. Hase, E. Biyik, A. Dragan, D. Krueger, D. Sadigh, and D. Hadfield-Menell. Trans. Mach. Learn. Res., (2023)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

Tomasz Kupka

Ascheablagerungsprobleme bei der Mitverbrennung von alternativen Brennstoffen in SteinkohlekraftwerkenT. Kupka. TU Clausthal-Zellerfeld, (2009)

Tomasz Wocjan

Dynamics of DNA in nucleosomes and plasmids studied by Brownian dynamicsT. Wocjan. Uni Heidelberg, (2009)

Tomasz Trela

Tomasz Zyss

Tomasz Mistrzyk

Other publications of authors with the same name

On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting.T. Korbak, H. Elsahar, G. Kruszewski, and M. Dymetman. NeurIPS, (2022)Towards Understanding Sycophancy in Language Models.M. Sharma, M. Tong, T. Korbak, D. Duvenaud, A. Askell, S. Bowman, N. Cheng, E. Durmus, Z. Hatfield-Dodds, S. Johnston and 9 other author(s). CoRR, (2023)Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication.L. Kucinski, T. Korbak, P. Kolodziej, and P. Milos. NeurIPS, page 23075-23088. (2021)Foundational Challenges in Assuring Alignment and Safety of Large Language Models.U. Anwar, A. Saparov, J. Rando, D. Paleka, M. Turpin, P. Hase, E. Lubana, E. Jenner, S. Casper, O. Sourbut and 28 other author(s). CoRR, (2024)Inverse Scaling: When Bigger Isn't Better.I. McKenzie, A. Lyzhov, M. Pieler, A. Parrish, A. Mueller, A. Prabhu, E. McLean, A. Kirtland, A. Ross, A. Liu and 17 other author(s). Trans. Mach. Learn. Res., (2023)RL with KL penalties is better viewed as Bayesian inference.T. Korbak, E. Perez, and C. Buckley. EMNLP (Findings), page 1083-1091. Association for Computational Linguistics, (2022)Towards Understanding Sycophancy in Language Models.M. Sharma, M. Tong, T. Korbak, D. Duvenaud, A. Askell, S. Bowman, E. Durmus, Z. Hatfield-Dodds, S. Johnston, S. Kravec and 8 other author(s). ICLR, OpenReview.net, (2024)Taken out of context: On measuring situational awareness in LLMs.L. Berglund, A. Stickland, M. Balesni, M. Kaufmann, M. Tong, T. Korbak, D. Kokotajlo, and O. Evans. CoRR, (2023)Controlling Conditional Language Models without Catastrophic Forgetting.T. Korbak, H. Elsahar, G. Kruszewski, and M. Dymetman. ICML, volume 162 of Proceedings of Machine Learning Research, page 11499-11528. PMLR, (2022)The Emergence of Action-grounded Compositional Communication.K. Glówka, M. Niklewski, J. Wiszowata, T. Korbak, J. Raczaszek-Leonardi, and J. Zubek. CogSci, cognitivesciencesociety.org, (2020)

BibSonomy

Disambiguation of "Korbak, Tomasz"

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

Please choose a person to relate this publication to

Tomasz Kupka

Tomasz Wocjan

Tomasz Trela

Tomasz Zyss

Tomasz Mistrzyk

Other publications of authors with the same name

Disambiguation

BibSonomy

Disambiguation of "Korbak, Tomasz"

copydeleteadd this publication to your clipboardcommunity posthistory of this postURLDOIBibTeXEndNoteAPAChicagoDIN 1505HarvardMSOffice XML Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

Please choose a person to relate this publication to

Tomasz Kupka

Tomasz Wocjan

Tomasz Trela

Tomasz Zyss

Tomasz Mistrzyk

Other publications of authors with the same name

Disambiguation

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.