4 papers
Latent Taxonomies: How Property Induction Develops in Language Model Pre-training
Jan Sobotka, Ekaterina Goliakova, Marcin Detyniecki +2
When told that robins have sesamoid bones, people are far more prone to extend the property to sparrows than to whales. This behavior, called category-based property induction, is…
Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
Jan Sobotka, Mustafa O. Karabag, Ufuk Topcu
Large language models (LLMs) are increasingly tasked with strategic decision-making under incomplete information, such as in negotiation and policymaking. While LLMs can excel at m…
Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game
Mustafa O. Karabag, Jan Sobotka, Ufuk Topcu
Large language model-based (LLM-based) agents have become common in settings that include non-cooperative parties. In such settings, agents' decision-making needs to conceal inform…
Investigation into the Training Dynamics of Learned Optimizers
Jan Sobotka, Petr Šimánek, Daniel Vašata
Optimization is an integral part of modern deep learning. Recently, the concept of learned optimizers has emerged as a way to accelerate this optimization process by replacing trad…