UCL study finds LLMs share a Fisher-Rao information geometry that enables low-distortion model interventions

UniversityCollegeLondon · hf · 2026-09-23

Researchers from University College London published a study arguing that the Fisher-Rao information geometry of next-token probabilities is shared across LLM architectures, making model behavior linked, learnable, and controllable.

Original post →

More from Research

Research channel →