6 citations · 6 across the 16 of their papers we have counts for
8 papers · 1 filter
The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors
Toni J. B. Liu, Jiajun Bao, Yizhou Liu +4
What does a language model predict when it has few clues? The answer lurks in its unembedding geometry: a single direction of the unembedding matrix encodes the unigram distributio…
A Graph Signal Processing Perspective on Numerical Sequence Representations in LLM In-Context Learning
Jiajun Bao, Zihao Qi, Toni J. B. Liu +4
Pretrained large language models (LLMs) have demonstrated in-context learning (ICL) capabilities for numerical inference over sequences serialized as text. Prior work has identifie…
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
Leon Bergen, Usha Bhalla, Sidharth Baskaran +14
Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. Th…
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Daniel Wurgaft, Can Rager, Matthew Kowal +13
Neural representations carry rich geometric structure; but does that structure causally shape behavior? To address this question, we intervene along paths through activation space…
Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics, Revealing a Three-Stage In-Context Learning Mechanism
Jiajun Bao, Nicolas Boullé, Toni J. B. Liu +2
Large language models (LLMs) have demonstrated emergent in-context learning (ICL) capabilities across a range of tasks, including zero-shot time-series forecasting. We show that te…
Density estimation with LLMs: a geometric investigation of in-context learning trajectories
Toni J. B. Liu, Nicolas Boullé, Raphaël Sarfati +1
Large language models (LLMs) demonstrate remarkable emergent abilities to perform in-context learning across various tasks, including time series forecasting. This work investigate…
Lines of Thought in Large Language Models
Raphaël Sarfati, Toni J. B. Liu, Nicolas Boullé +1
Large Language Models achieve next-token prediction by transporting a vectorized piece of text (prompt) across an accompanying embedding space under the action of successive transf…
LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law
Toni J. B. Liu, Nicolas Boullé, Raphaël Sarfati +1
Pretrained large language models (LLMs) are surprisingly effective at performing zero-shot tasks, including time-series forecasting. However, understanding the mechanisms behind su…