Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models

Darpan Aswal, Thomas Palmeira Ferraz, Yongxin Zhou, Maxime Peyrard

Preprint - Under Review

TL;DR: Latent reasoning models can display human-observable patterns that look like reasoning but are not causally needed for the output, thus not evidence of mechanism. We argue that latent thoughts should be treated as hidden computation, not hidden explanation, and that LRM interpretability needs matched controls and causal interventions.

ARXIV BIB PDF

Mechanistic Interpretability Latent Reasoning Causal Tracing Geometric Analysis