Divergence controls entropy in distillation

arXiv:2610.03529 · cs.LG, cs.CL · Submitted 2026-10-02 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-10-02

Updated: 2026-10-02

Code: https://github.com/NicolasZucchet/Entropy-in-distillation

Terminology

• Distillation — 1× in this paper · explained in 2 episodes

Sources

• Training Verifiers to Solve Math Word Problems
• The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• Gemma 3 Technical Report
• Distilling the Knowledge in a Neural Network
• Scaling Laws for Neural Language Models
• Diverse Preference Optimization
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
• On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
• Olmo 3
• MiMo-V2-Flash Technical Report
• Trust Region On-Policy Distillation
• Qwen3 Technical Report
• Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
• Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks