Raphaël Sarfati

According to our database, Raphaël Sarfati authored at least 9 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought.

Siddharth Boppana, Annabel Ma, Max Loeffler, Raphaël Sarfati, Eric Bigelow, Atticus Geiger, Owen Lewis, Jack Merullo

CoRR, March, 2026

The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors.

Raphaël Sarfati, Eric J. Bigelow, Daniel Wurgaft, Jack Merullo, Atticus Geiger, Owen Lewis, Tom McGrath, Ekdeep Singh Lubana

CoRR, February, 2026

Jacobian Scopes: token-level causal attributions in LLMs.

Toni J. B. Liu, Baran Zadeoglu, Nicolas Boullé, Raphaël Sarfati, Christopher J. Earls

CoRR, January, 2026

2025

Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics.

Jiajun Bao, Nicolas Boullé, Toni J. B. Liu, Raphaël Sarfati, Christopher J. Earls

CoRR, September, 2025

Lines of Thought in Large Language Models.

Raphaël Sarfati, Toni J. B. Liu, Nicolas Boullé, Christopher J. Earls

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Density estimation with LLMs: a geometric investigation of in-context learning trajectories.

Toni J. B. Liu, Nicolas Boullé, Raphaël Sarfati, Christopher J. Earls

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

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

Raphaël Sarfati, Haley Moller, Toni J. B. Liu, Nicolas Boullé, Christopher J. Earls

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024

Tracking and triangulating firefly flashes in field recordings.

Raphaël Sarfati

CoRR, 2024

LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law.

Toni J. B. Liu, Nicolas Boullé, Raphaël Sarfati, Christopher J. Earls

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024