A switching linear dynamical system on a 40-dimensional projection of LLM hidden states captures about half the variance of reasoning trajectories and predicts belief shifts during adversarial prompts.
Language models are few-shot learners
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Statistical Physics of Language Model Reasoning
A switching linear dynamical system on a 40-dimensional projection of LLM hidden states captures about half the variance of reasoning trajectories and predicts belief shifts during adversarial prompts.