Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation
cs.LG, cs.AI, cs.CL
Submitted: 2026-09-02
Updated: 2026-09-16
Comments: 17 pages, 6 figures, 7 tables
Code: https://github.com/THUDM/slime
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- Reward-Gated On-Policy Distillation
- RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
- Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
- MiniLLM: On-Policy Distillation of Large Language Models
- Entropy-Aware On-Policy Distillation of Language Models
- Scaling Reasoning Efficiently via Relaxed On-Policy Distillation
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Small Models Struggle to Learn from Strong Reasoners
- Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model
- When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
- Understanding R1-Zero-Like Training: A Critical Perspective
- MiMo-V2-Flash Technical Report
- MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
- SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
- A Survey of On-Policy Distillation for Large Language Models
- GATES: Self-Distillation under Privileged Context with Consensus Gating
- REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy 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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks