Shuffled OPSD: When Semantic Consistency Hurts On-Policy Self-Distillation?
cs.CL, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation
- MiniLLM: On-Policy Distillation of Large Language Models
- Distilling the Knowledge in a Neural Network
- LoRA: Low-Rank Adaptation of Large Language Models
- Rethinking On-Policy Self-Distillation for Thinking Models
- DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
- Understanding R1-Zero-Like Training: A Critical Perspective
- Unifying distillation and privileged information
- Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Distillation Enables Continual Learning
- Learning by Distilling Context
- Finetuned Language Models Are Zero-Shot Learners
- Qwen3 Technical Report
- On-Policy Context Distillation for Language Models
- STaR: Bootstrapping Reasoning With Reasoning
- What Does Privileged Information Add to On-Policy Self-Distillation?
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
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