Verification-Aware Training for Speculative Decoding

arXiv:2608.30135 · cs.CL · Submitted 2026-08-31 · Read on arXiv

cs.CL

Submitted: 2026-08-31

Updated: 2026-08-31

Comments: 14 pages

Code: https://github.com/naver-ai/vat

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

Terminology

• Verification — 147× in this paper · explained in 2 episodes
• Speculative Decoding — 26× in this paper · explained in 2 episodes
• Adaptive Weighting — 15× in this paper · explained in 1 episode
• Verification-Aware Training — 11× in this paper
• Benchmark — 9× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Alignment — 5× in this paper · explained in 1 episode
• Block Diffusion — 4× in this paper · explained in 2 episodes
• Distillation — 4× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 3× in this paper
• Transformer — 3× in this paper · explained in 2 episodes
• In International Conference on Machine Learning — 2× in this paper
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment Distillation — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• In Conference on Language Modeling — 1× in this paper
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
• Program Synthesis with Large Language Models
• Draft, Verify, and Improve: Toward Training-Aware Speculative Decoding
• Accelerating Large Language Model Decoding with Speculative Sampling
• DFlash: Block Diffusion for Flash Speculative Decoding
• Evaluating Large Language Models Trained on Code
• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation
• Distilling the Knowledge in a Neural Network
• DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
• DeepSeek-V3 Technical Report
• SpecDiff-2: Scaling Diffusion Drafter Alignment For Faster Speculative Decoding
• Gemini: A Family of Highly Capable Multimodal Models
• D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
• The Perfect Blend: Redefining RLHF with Mixture of Judges
• Qwen3 Technical Report

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