Reasoning in LLMs emerges from inference dynamics forming constrained low-dimensional manifolds that preserve non-degenerate information volume, rather than from compression alone.
Chain-of-thought prompting elicits reasoning in large language models.Advances in neural infor- mation processing systems, 35:24824–24837
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Reasoning emerges from constrained inference manifolds in large language models
Reasoning in LLMs emerges from inference dynamics forming constrained low-dimensional manifolds that preserve non-degenerate information volume, rather than from compression alone.