Meet Students Where They Are: Student-Prefix Teacher Adaptation for On-Policy Distillation
cs.CL
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/THUDM/slime
Terminology
Sources
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
- MiniLLM: On-Policy Distillation of Large Language Models
- JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
- Distilling the Knowledge in a Neural Network
- Rethinking On-Policy Self-Distillation for Thinking Models
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Multi-Turn On-Policy Distillation with Prefix Replay
- When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
- Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
- Decoupled Weight Decay Regularization
- Sequence Level Training with Recurrent Neural Networks
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- A Survey of On-Policy Distillation for Large Language Models
- SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
- On the Position Bias of On-Policy Distillation
- TIP: Token Importance in On-Policy Distillation
- Qwen3 Technical Report
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data