Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States

arXiv:2602.03708 · cs.CL, cs.PF · Submitted 2026-02-03 · Read on arXiv

cs.CL, cs.PF

Submitted: 2026-02-03

Updated: 2026-08-31

Comments: EMNLP2026 Main

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

Terminology

• Speculative Decoding — 45× in this paper · explained in 2 episodes
• Verification — 21× in this paper · explained in 2 episodes
• Benchmark — 8× in this paper · explained in 2 episodes
• Clustering — 7× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Generalization — 4× in this paper · explained in 13 episodes
• Adam — 3× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 3× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Token Per Second — 1× in this paper
• Trace — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Qwen Technical Report
• Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
• A Survey on LLM-as-a-Judge
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Measuring Mathematical Problem Solving With the MATH Dataset
• OpenAI o1 System Card
• Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
• Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
• Evaluating Scoring Bias in LLM-as-a-Judge
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning
• DeepSeek-V3 Technical Report
• Decoupled Weight Decay Regularization
• SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
• s1: Simple test-time scaling
• SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
• GPT-4 Technical Report
• Accelerating LLM Inference with Staged Speculative Decoding
• Gemma: Open Models Based on Gemini Research and Technology
• Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges
• LLaMA: Open and Efficient Foundation Language Models

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