Reasoning accuracy in latent CoT depends on mutual information fidelity between latent trajectories and explicit steps, with generative reconstruction preserving capacity better than geometric compression.
What Happened in LLM s Layers when Trained for Fast vs
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Defines Entropy-Gradient Inversion as a negative entropy-gradient correlation fingerprinting LRM reasoning and proposes CorR-PO to embed it in RL regularization, claiming consistent outperformance on benchmarks.
citing papers explorer
-
What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis
Reasoning accuracy in latent CoT depends on mutual information fidelity between latent trajectories and explicit steps, with generative reconstruction preserving capacity better than geometric compression.
-
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
Defines Entropy-Gradient Inversion as a negative entropy-gradient correlation fingerprinting LRM reasoning and proposes CorR-PO to embed it in RL regularization, claiming consistent outperformance on benchmarks.