Fisher-Informed Recalibration for Feedback-Based On-Policy Self-Distillation of LLMs

arXiv:2609.34009 · cs.LG · Submitted 2026-09-27 · Read on arXiv

cs.LG

Submitted: 2026-09-27

Updated: 2026-09-27

Comments: 30 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

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

Sources

• On the Opportunities and Risks of Foundation Models
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs
• The Llama 3 Herd of Models
• Distilling the Knowledge in a Neural Network
• LoRA: Low-Rank Adaptation of Large Language Models
• Reinforcement Learning via Self-Distillation
• TAP: Two-Stage Adaptive Personalization of Multi-Task and Multi-Modal Foundation Models in Federated Learning
• Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning
• Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
• DemoPSD: Disagreement-Modulated Policy Self-Distillation
• Decoupled Weight Decay Regularization
• Large Language Models: A Survey
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Self-Distillation Enables Continual Learning
• SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
• Trust Region Policy Distillation
• Trust Region On-Policy Distillation
• A Survey on Knowledge Distillation of 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