Self-distillation token rewards measure input-response-feedback pointwise mutual information, and CREDIT extracts the input-specific component with contrastive baselines to improve LLM reasoning performance.
A new learning paradigm: Learning using privileged information.Neural networks, 22(5-6):544–557
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 3years
2026 3roles
background 2polarities
background 2representative citing papers
Anti-Self-Distillation reverses self-distillation signals via PMI to fix overconfidence on structural tokens, matching GRPO baseline accuracy 2-10x faster with up to 11.5 point gains across 4B-30B models.
Hybrid LSTM-QCBM model outperforms classical LSTM on SSE Composite and CSI 300 volatility forecasting and supports quantum-assisted training followed by fully classical inference.
citing papers explorer
-
From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation
Self-distillation token rewards measure input-response-feedback pointwise mutual information, and CREDIT extracts the input-specific component with contrastive baselines to improve LLM reasoning performance.
-
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Anti-Self-Distillation reverses self-distillation signals via PMI to fix overconfidence on structural tokens, matching GRPO baseline accuracy 2-10x faster with up to 11.5 point gains across 4B-30B models.
-
A Hybrid Quantum-Classical Framework for Financial Volatility Forecasting Based on Quantum Circuit Born Machines
Hybrid LSTM-QCBM model outperforms classical LSTM on SSE Composite and CSI 300 volatility forecasting and supports quantum-assisted training followed by fully classical inference.