Reasoning in LLMs produces a transient geometric pulse in which concept manifolds untangle into linearly separable subspaces immediately before computation and compress afterward.
The geometry of prompting: Unveiling distinct mechanisms of task adaptation in language models.arXiv preprint arXiv:2502.08009,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Emergent Manifold Separability during Reasoning in Large Language Models
Reasoning in LLMs produces a transient geometric pulse in which concept manifolds untangle into linearly separable subspaces immediately before computation and compress afterward.