Preprint

Latent Taxonomies: How Property Induction Develops in Language Model Pre-training
When told that robins have sesamoid bones, people are far more prone to extend the property to sparrows than to whales. This behavior, …
Jan Sobotka, Ekaterina Goliakova, Marcin Detyniecki, Antoine Bosselut, Xavier Renard
PDF DOI
Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
Large language models (LLMs) are increasingly tasked with strategic decision-making under incomplete information, such as in …
Jan Sobotka, Mustafa O. Karabag, Ufuk Topcu
PDF DOI
Enhancing Fractional Gradient Descent with Learned Optimizers
Fractional Gradient Descent (FGD) offers a novel and promising way to accelerate optimization by incorporating fractional calculus into …
Jan Sobotka, Petr Šimánek, Pavel Kordík
PDF DOI