The Stepwise Informativeness Assumption explains the correlation between LLM entropy dynamics and reasoning correctness by positing that correct traces accumulate answer-relevant information stepwise during generation.
Title resolution pending
2 Pith papers cite this work, alongside 290 external citations. Polarity classification is still indexing.
2
Pith papers citing it
290
external citations · OpenAlex
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DQMW-Sample realizes a classically hard online learning primitive via dissipative quantum dynamics with sublinear regret and proven hardness for classical simulation including PH collapse.
citing papers explorer
-
The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
The Stepwise Informativeness Assumption explains the correlation between LLM entropy dynamics and reasoning correctness by positing that correct traces accumulate answer-relevant information stepwise during generation.
-
Dissipative Quantum Multiplicative Weights with Sampling Feedback: A Classically Hard Primitive Realized via Engineered Open-System Dynamics
DQMW-Sample realizes a classically hard online learning primitive via dissipative quantum dynamics with sublinear regret and proven hardness for classical simulation including PH collapse.