To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals

arXiv:2609.20186 · cs.CL · Submitted 2026-09-17 · Read on arXiv

cs.CL

Submitted: 2026-09-17

Updated: 2026-09-17

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

Terminology

• Speculative Decoding — 10× in this paper · explained in 2 episodes
• Large Language Model — 9× in this paper
• Transformer — 9× in this paper · explained in 2 episodes
• AUC — 4× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Verification — 4× in this paper · explained in 2 episodes
• KV cache — 3× in this paper · explained in 3 episodes
• Prompt Lookup Decoding — 3× in this paper
• Ablation Studies — 2× in this paper · explained in 1 episode
• Distillation — 2× in this paper · explained in 2 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes

Sources

• Accelerating Large Language Model Decoding with Speculative Sampling
• CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality
• Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs
• The Llama 3 Herd of Models
• Measuring Mathematical Problem Solving With the MATH Dataset
• Teaching Machines to Read and Comprehend
• BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms
• EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
• EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
• In-context Learning and Induction Heads
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
• Qwen3 Technical Report
• DistillSpec: Improving Speculative Decoding via Knowledge Distillation

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