9 papers
Persona Cartography: Charting Language Model Personality Traits in Weight Space
Luke Baines, Anton Gonzalvez Hawthorne, Mariia Koroliuk +4
Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and control…
Can Vision Language Models Learn Intuitive Physics from Interaction?
Luca M. Schulze Buschoff, Konstantinos Voudouris, Can Demircan +1
Pre-trained vision language models do not have good intuitions about the physical world. Recent work has shown that supervised fine-tuning can improve model performance on simple p…
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…
In-Context Function Learning in Large Language Models
Elif Akata, Konstantinos Voudouris, Vincent Fortuin +1
Large language models (LLMs) can learn from a few demonstrations provided at inference time. We study this in-context learning phenomenon through the lens of Gaussian Processes (GP…
Measuring What AI Systems Might Do: Towards A Measurement Science in AI
Konstantinos Voudouris, Mirko Thalmann, Alex Kipnis +2
Scientists, policy-makers, business leaders, and members of the public care about what modern artificial intelligence systems are disposed to do. Yet terms such as capabilities, pr…
Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models
Luca M. Schulze Buschoff, Konstantinos Voudouris, Elif Akata +3
Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual st…