Know Thyself, Teach Thyself: Internal Information Flow for Selective Self-Distillation

arXiv:2609.36695 · cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.LG

Submitted: 2026-09-29

Updated: 2026-10-04

Code: https://github.com/1240148048/INFLOW

Terminology

• Distillation — 1× in this paper · explained in 2 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes

Sources

• Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
• SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
• Distilling the Knowledge in a Neural Network
• Reinforcement Learning via Self-Distillation
• Ministral 3
• The Llama 3 Herd of Models
• PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning
• Qwen3 Technical Report
• MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
• On-Policy Context Distillation for Language Models
• Self-Rewarding Language Models

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks