Masked Self-Distillation: Internalizing the Chain-of-Thought in Language Models
cs.AI, cs.CL
Submitted: 2026-06-18
Updated: 2026-09-30
Terminology
Sources
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
- Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation
- Training Verifiers to Solve Math Word Problems
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- Distilling the Knowledge in a Neural Network
- Reinforcement Learning via Self-Distillation
- O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
- Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- Self-Distillation Enables Continual Learning
- HybridFlow: A Flexible and Efficient RLHF Framework
- Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
- Learning by Distilling Context
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens
- Qwen2 Technical Report
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection