Inductive Feedback for Mixed-Policy Distillation
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation
- SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
- Calibrating Teacher--Student Discrepancy for On-Policy Distillation
- DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
- EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation
- On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
- Privileged Information Distillation for Language Models
- Self-Distillation Enables Continual Learning
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
- Expanding the Capabilities of Reinforcement Learning via Text Feedback
- ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
- On the Position Bias of On-Policy Distillation
- Formalizing Learning from Language Feedback with Provable Guarantees
- Qwen3 Technical Report
- OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning
- Weak-to-Strong On-Policy Distillation
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large 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