Nucleus Speculative Decoding: Plausibility-Aware Verification Beyond Exact Distribution

arXiv:2610.07822 · cs.CL · Submitted 2026-10-06 · Read on arXiv

cs.CL

Submitted: 2026-10-06

Updated: 2026-10-11

Code: https://github.com/EIT-NLP/Nucleus-Speculative-Decoding

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

Terminology

• Speculative Decoding — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Program Synthesis with Large Language Models
• Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
• Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
• Accelerating Large Language Model Decoding with Speculative Sampling
• DFlash: Block Diffusion for Flash Speculative Decoding
• Evaluating Large Language Models Trained on Code
• DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
• Training Verifiers to Solve Math Word Problems
• DeepSeek-V3 Technical Report
• Approximate Speculative Decoding
• Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding
• Better & Faster Large Language Models via Multi-token Prediction
• Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
• Measuring Mathematical Problem Solving With the MATH Dataset
• Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff
• The Curious Case of Neural Text Degeneration
• Fast Inference from Transformers via Speculative Decoding
• EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees
• EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
• EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

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