SAPD: Step-Aligned Privileged Distillation

arXiv:2610.09665 · cs.CL · Submitted 2026-10-07 · Read on arXiv

cs.CL

Submitted: 2026-10-07

Updated: 2026-10-07

Comments: preprint

Code: https://github.com/Miaow-Lab/SAPD

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

Terminology

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

Sources

• Program Synthesis with Large Language Models
• Evaluating Large Language Models Trained on Code
• Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
• Distilling the Knowledge in a Neural Network
• Unifying distillation and privileged information
• Solving math word problems with process- and outcome-based feedback
• Embarrassingly Simple Self-Distillation Improves Code Generation
• StepOPSD: Step-Aware Online Preference Self-Distillation for Agent Reinforcement Learning
• SOD: Step-wise On-policy Distillation for Small Language Model Agents

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