4 papers
Large Language Models Develop Belief State Geometry In-Context
Daniel Balcells, Andrew Jun Lee, Chirag Rastogi +3
Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that support ICL remain poorly underst…
Linear Personality Probing and Steering in LLMs: A Big Five Study
Michel Frising, Daniel Balcells
Large language models (LLMs) exhibit distinct and consistent personalities that greatly impact trust and engagement. While this means that personality frameworks would be highly va…
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Bo Liu, Leon Guertler, Simon Yu +9
Recent advances in reinforcement learning have shown that language models can develop sophisticated reasoning through training on tasks with verifiable rewards, but these approache…
Evolution of SAE Features Across Layers in LLMs
Daniel Balcells, Benjamin Lerner, Michael Oesterle +2
Sparse Autoencoders for transformer-based language models are typically defined independently per layer. In this work we analyze statistical relationships between features in adjac…