Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall

arXiv:2609.01532 · cs.CL · Submitted 2026-09-01 · Read on arXiv

cs.CL

Submitted: 2026-09-01

Updated: 2026-09-20

Code: https://github.com/facebookresearch/midtraining-distillation

Terminology

• Distillation — 164× in this paper · explained in 2 episodes
• Switch Distillation — 56× in this paper
• Knowledge Distillation — 26× in this paper · explained in 11 episodes
• AUC — 21× in this paper · explained in 2 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Alignment — 5× in this paper · explained in 1 episode
• Adam — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• On-Policy Distillation — 3× in this paper · explained in 3 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Catastrophic Forgetting — 2× in this paper · explained in 5 episodes
• Entropy-Aware On-Policy Distillation — 2× in this paper
• Foundation Model — 2× in this paper · explained in 3 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Test-time Scaling — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
• The Llama 3 Herd of Models
• Textbooks Are All You Need
• Measuring Massive Multitask Language Understanding
• ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution
• Entropy-Aware On-Policy Distillation of Language Models
• Why Fine-Tuning Encourages Hallucinations and How to Fix It
• Data-efficient pre-training by scaling synthetic megadocs
• Sequence-Level Knowledge Distillation
• Slicing and Dicing: Configuring Optimal Mixtures of Experts
• Let's Verify Step by Step
• Midtraining Bridges Pretraining and Posttraining Distributions
• Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
• Improved Knowledge Distillation via Teacher Assistant
• Olmo 3
• Progressive distillation induces an implicit curriculum
• WinoGrande: An Adversarial Winograd Schema Challenge at Scale
• Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

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