OPSRD: On-Policy Self-Role Distillation

arXiv:2609.39884 · cs.CL, cs.AI, cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/zhansan114514/OPSRD

Terminology

• Distillation — 47× in this paper · explained in 2 episodes
• Accuracy — 24× in this paper · explained in 1 episode
• Benchmark — 17× in this paper · explained in 2 episodes
• Ablation — 10× in this paper · explained in 1 episode
• On-Policy Distillation — 9× in this paper · explained in 3 episodes
• Self-Distillation — 7× in this paper · explained in 7 episodes
• Knowledge Distillation — 4× in this paper · explained in 11 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
• Reinforced Self-Training (ReST) for Language Modeling
• Distilling the Knowledge in a Neural Network
• In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models
• Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
• When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation
• Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks
• CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation
• Learning by Distilling Context
• ExpertPrompting: Instructing Large Language Models to be Distinguished Experts
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering