activity
20242026
collaborators

7 papers

cs.LG2026

A Graph Signal Processing Perspective on Numerical Sequence Representations in LLM In-Context Learning

Jiajun Bao, Zihao Qi, Toni J. B. Liu +6

Pretrained large language models (LLMs) have demonstrated in-context learning (ICL) capabilities for numerical inference over sequences serialized as text. Prior work has identifie…

cs.CL2026

Jacobian Scopes: token-level causal attributions in LLMs

Toni J. B. Liu, Baran Zadeoğlu, Nicolas Boullé +3

Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prio…

cs.LG2026

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…

cs.CL2025

What's in a prompt? Language models encode literary style in prompt embeddings

Raphaël Sarfati, Haley Moller, Toni J. B. Liu +2

Large language models use high-dimensional latent spaces to encode and process textual information. Much work has investigated how the conceptual content of words translates into g…

cs.LG2025

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…

cs.LG2025

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…