Tomasz Korbak

Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Stephen Casper, Xander Davies, Claudia Shi et al. · arXiv (Cornell University) · 2023 · 92 citations · Full text

Computing, Computer Science, Artificial Intelligence +12

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"

Lukas Berglund, Meg Tong, Max Kaufmann et al. · arXiv (Cornell University) · 2023 · 32 citations · Full text

Computing, Computer Science, Computational Linguistics +8

Pretraining Language Models with Human Preferences

Tomasz Korbak, Kejian Shi, Angelica Chen et al. · arXiv (Cornell University) · 2023 · 26 citations · Full text

Computing, Computer Science, Computational Linguistics +16

Developmentally motivated emergence of compositional communication via template transfer

Tomasz Korbak, Julian Zubek, Łukasz Kuciński et al. · arXiv (Cornell University) · 2019 · 25 citations · Full text

Language Studies, Communication, Linguistics +16

Computational enactivism under the free energy principle

Tomasz Korbak · Synthese · 2019 · 23 citations · Full text

Humanities, Philosophy, Cognitive Psychology +11