Resampling subsequent text in chain-of-thought traces enables causal analysis of partial reasoning steps in LLMs, showing limited causal impact from self-preservation statements and advantages of on-policy interventions over off-policy edits.
Forking paths in neural text generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.
citing papers explorer
-
Thought Branches: Interpreting LLM Reasoning Requires Resampling
Resampling subsequent text in chain-of-thought traces enables causal analysis of partial reasoning steps in LLMs, showing limited causal impact from self-preservation statements and advantages of on-policy interventions over off-policy edits.
-
When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.