Dual-Vocabulary Language Model for Cross-Tokenizer Distillation

arXiv:2609.33816 · cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/mlfoundations/evalchemy

Terminology

• Distillation — 81× in this paper · explained in 2 episodes
• Alignment — 25× in this paper · explained in 1 episode
• Tokenization — 25× in this paper · explained in 2 episodes
• Benchmark — 20× in this paper · explained in 2 episodes
• On-Policy Distillation — 11× in this paper · explained in 3 episodes
• Hybrid-Prefix Attention — 9× in this paper
• Knowledge Distillation — 6× in this paper · explained in 11 episodes
• Parallel-Tokenized Sequence — 6× in this paper
• Ablation — 5× in this paper · explained in 1 episode
• Decode — 4× in this paper · explained in 2 episodes
• GRPO — 4× in this paper · explained in 6 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Aggregation — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Optimal Transport — 3× in this paper · explained in 5 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Ablation study — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
• Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models
• SRA: Span Representation Alignment for Large Language Model Distillation
• Stream of Search (SoS): Learning to Search in Language
• Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit
• CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
• MiniLLM: On-Policy Distillation of Large Language Models
• Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models
• Skywork Open Reasoner 1 Technical Report
• Measuring Massive Multitask Language Understanding
• Distilling the Knowledge in a Neural Network
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• From Principles to Applications: A Comprehensive Survey of Discrete Tokenizers in Generation, Comprehension, Recommendation, and Information Retrieval
• DistiLLM: Towards Streamlined Distillation for Large Language Models
• Let's Verify Step by Step
• ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation
• Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
• CTPD: Cross Tokenizer Preference Distillation

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection