8 papers
Post-training makes large language models less human-like
Marcel Binz, Elif Akata, Abdullah Almaatouq +76
Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, w…
Reference-Free Rating of LLM Responses via Latent Information
Leander Girrbach, Chi-Ping Su, Tankred Saanum +3
How reliable are single-response LLM-as-a-judge ratings without references, and can we obtain fine-grained, deterministic scores in this setting? We study the common practice of as…
A circuit for predicting hierarchical structure in-context in Large Language Models
Tankred Saanum, Can Demircan, Samuel J. Gershman +1
Large Language Models (LLMs) excel at in-context learning, the ability to use information provided as context to improve prediction of future tokens. Induction heads have been argu…
Centaur: a foundation model of human cognition
Marcel Binz, Elif Akata, Matthias Bethge +37
Establishing a unified theory of cognition has been a major goal of psychology. While there have been previous attempts to instantiate such theories by building computational model…
Evaluating alignment between humans and neural network representations in image-based learning tasks
Can Demircan, Tankred Saanum, Leonardo Pettini +5
Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. W…
Simplifying Latent Dynamics with Softly State-Invariant World Models
Tankred Saanum, Peter Dayan, Eric Schulz
To solve control problems via model-based reasoning or planning, an agent needs to know how its actions affect the state of the world. The actions an agent has at its disposal ofte…