Skip to results
MLSift
← Feed
NLP & Language ModelsTransformer2608.00828

Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models

Okan S. Coskun, Florian Rottach, Carsten Eickhoff, William Rudman

cs.AI

Abstract

We investigate the geometry of decision-making in Multiple Choice Question Answering (MCQA) through the lens of isotropy. Analyzing five open-weight models across diverse datasets, we identify decision-critical transition layers characterized by a shift in isotropy, coinciding with a major representational change and the emergence of task-relevant clusters. We demonstrate that this synchronized geometric behavior is strongly correlated with downstream accuracy ($r\approx0.84$), displaying its relevance for successful decision-making. Furthermore, we show that this transition is robust to prompt variations, suggesting that it reflects a general mechanism of model behavior.

Topics

Classified with taxonomy v2 on Sat, 5 Sept 2026.

The PDF is 1–3 MB. Open it in your browser's viewer, or load it here.

Open PDF