Across five LLMs, a sharp decrease in embedding isotropy at a critical layer predicts multiple-choice accuracy, with Spearman correlations up to -0.92.
Exploring the Sensitivity of LLM s' Decision-Making Capabilities: Insights from Prompt Variations and Hyperparameters
1 Pith paper cite this work, alongside 28 external citations. Polarity classification is still indexing.
1
Pith paper citing it
28
external citations · OpenAlex
fields
cs.AI 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models
Across five LLMs, a sharp decrease in embedding isotropy at a critical layer predicts multiple-choice accuracy, with Spearman correlations up to -0.92.