Tomasz Korbak
University of Sussex(GB)
Publications by Year
Research Areas
Topic Modeling, Natural Language Processing Techniques, Embodied and Extended Cognition, Language and cultural evolution, Philosophy and History of Science
Most-Cited Works
- → Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback(2023)89 cited
- → The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"(2023)31 cited
- → Pretraining Language Models with Human Preferences(2023)26 cited
- → Developmentally motivated emergence of compositional communication via template transfer(2019)25 cited
- → Computational enactivism under the free energy principle(2019)23 cited
- → Inverse Scaling: When Bigger Isn't Better(2023)22 cited
- → Catalytic Role Of Noise And Necessity Of Inductive Biases In The\n Emergence Of Compositional Communication(2021)20 cited
- → Training Language Models with Language Feedback at Scale(2023)16 cited
- → Foundational Challenges in Assuring Alignment and Safety of Large Language Models(2024)14 cited
- → Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data(2024)12 cited