Tomasz Korbak
Publication record assembled from the DBLP archive of ranked conferences.
Papers indexed
8
Venues
4
Active years
2020–2024
Best venue rank
A*
Where they publish
Papers
8 indexed papers, newest first.
| Year | Venue | Title | Authors |
|---|---|---|---|
| 2024 | ICLR | The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A". | Lukas Berglund, Meg Tong, Maximilian Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, Owain Evans |
| 2024 | ICLR | Compositional Preference Models for Aligning LMs. | Dongyoung Go, Tomasz Korbak, Germn Kruszewski, Jos Rozen, Marc Dymetman |
| 2024 | ICLR | Towards Understanding Sycophancy in Language Models. | Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Esin Durmus, Zac Hatfield-Dodds, Scott R. Johnston, Shauna Kravec, Timothy Maxwell, Sam McCandlish, Kamal Ndousse, Oliver Rausch, Nicholas Schiefer, Da Yan, Miranda Zhang, Ethan Perez |
| 2023 | ICML | Aligning Language Models with Preferences through f-divergence Minimization. | Dongyoung Go, Tomasz Korbak, Germn Kruszewski, Jos Rozen, Nahyeon Ryu, Marc Dymetman |
| 2023 | ICML | Pretraining Language Models with Human Preferences. | Tomasz Korbak, Kejian Shi, Angelica Chen, Rasika Vinayak Bhalerao, Christopher L. Buckley, Jason Phang, Samuel R. Bowman, Ethan Perez |
| 2022 | EMNLP | RL with KL penalties is better viewed as Bayesian inference. | Tomasz Korbak, Ethan Perez, Christopher L. Buckley |
| 2022 | ICML | Controlling Conditional Language Models without Catastrophic Forgetting. | Tomasz Korbak, Hady Elsahar, Germn Kruszewski, Marc Dymetman |
| 2020 | CogSci | The Emergence of Action-grounded Compositional Communication. | Krzysztof Glwka, Michal Niklewski, Joanna Wiszowata, Tomasz Korbak, Joanna Raczaszek-Leonardi, Julian Zubek |