# Constrained Decoding with Speculative Lookaheads

arXiv: https://arxiv.org/abs/2412.10418 · HTML: https://mlsanity.com/paper/2412.10418/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 9 Dec 2024.

## Builds on (most cited first, 24 of 24)

- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024)
- [Beam Search Strategies for Neural Machine Translation](https://mlsanity.com/paper/1702.01806/) (2017)
- [Speculative Decoding with Big Little Decoder](https://mlsanity.com/paper/2302.07863/) (2023)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [Accelerating LLM Inference with Staged Speculative Decoding](https://mlsanity.com/paper/2308.04623/) (2023)
- [REST: Retrieval-Based Speculative Decoding](https://mlsanity.com/paper/2311.08252/) (2023)
- [NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints](https://mlsanity.com/paper/2010.12884/) (2020)
- [Controlled Decoding from Language Models](https://mlsanity.com/paper/2310.17022/) (2023)
- [Online Speculative Decoding](https://mlsanity.com/paper/2310.07177/) (2023)
- [Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding](https://mlsanity.com/paper/2402.12374/) (2024)
- [Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation](https://mlsanity.com/paper/2403.06988/) (2024)
- [Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model](https://mlsanity.com/paper/2310.09520/) (2023)
- [Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning](https://mlsanity.com/paper/2210.04242/) (2022)
- [Controlled Text Generation via Language Model Arithmetic](https://mlsanity.com/paper/2311.14479/) (2023)
- [Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism](https://mlsanity.com/paper/2406.03853/) (2024)
- [Faithfulness-Aware Decoding Strategies for Abstractive Summarization](https://mlsanity.com/paper/2303.03278/) (2023)
- [Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement](https://mlsanity.com/paper/2402.14160/) (2024)
- [FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs](https://mlsanity.com/paper/2403.05766/) (2024)
- [BASS: Batched Attention-optimized Speculative Sampling](https://mlsanity.com/paper/2404.15778/) (2024)

## Built on by (most cited first, 6 of 6)

- [Fast and Expressive Multi-Byte Prediction with Probabilistic Circuits](https://mlsanity.com/paper/2511.11346/) (2025)
- [Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars](https://mlsanity.com/paper/2602.00612/) (2026)
- [Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner](https://mlsanity.com/paper/2508.15044/) (2025)
- [XML Prompting as Grammar-Constrained Interaction: Fixed-Point Semantics, Convergence Guarantees, and Human-AI Protocols](https://mlsanity.com/paper/2509.08182/) (2025)
- [A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges](https://mlsanity.com/paper/2602.05883/) (2026)
- [Lost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval](https://mlsanity.com/paper/2604.23396/) (2026)

## Abstract (arXiv)

Constrained decoding with lookahead heuristics (CDLH) is a highly effective method for aligning LLM generations to human preferences. However, the extensive lookahead roll-out operations for each generated token makes CDLH prohibitively expensive, resulting in low adoption in practice. In contrast, common decoding strategies such as greedy decoding are extremely efficient, but achieve very low constraint satisfaction. We propose constrained decoding with speculative lookaheads (CDSL), a technique that significantly improves upon the inference efficiency of CDLH without experiencing the drastic performance reduction seen with greedy decoding. CDSL is motivated by the recently proposed idea of speculative decoding that uses a much smaller draft LLM for generation and a larger target LLM for verification. In CDSL, the draft model is used to generate lookaheads which is verified by a combination of target LLM and task-specific reward functions. This process accelerates decoding by reducing the computational burden while maintaining strong performance. We evaluate CDSL in two constraint decoding tasks with three LLM families and achieve 2.2x to 12.15x speedup over CDLH without significant performance reduction.