# Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation

arXiv: https://arxiv.org/abs/2403.06988 · HTML: https://mlsanity.com/paper/2403.06988/

## Key facts

- Cited by 101 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 7 Feb 2024.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [Synchromesh: Reliable code generation from pre-trained language models](https://mlsanity.com/paper/2201.11227/) (2022)

## Built on by (most cited first, 30 of 101)

- [Securing AI Agents with Information-Flow Control](https://mlsanity.com/paper/2505.23643/) (2025)
- [Formal Mathematical Reasoning: A New Frontier in AI](https://mlsanity.com/paper/2412.16075/) (2024)
- [Design Patterns for Securing LLM Agents against Prompt Injections](https://mlsanity.com/paper/2506.08837/) (2025)
- [Perception Tokens Enhance Visual Reasoning in Multimodal Language Models](https://mlsanity.com/paper/2412.03548/) (2024)
- [SynCode: LLM Generation with Grammar Augmentation](https://mlsanity.com/paper/2403.01632/) (2024)
- [Flexible and Efficient Grammar-Constrained Decoding](https://mlsanity.com/paper/2502.05111/) (2025)
- [Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation](https://mlsanity.com/paper/2406.16678/) (2024)
- [Moral Alignment for LLM Agents](https://mlsanity.com/paper/2410.01639/) (2024)
- [Type-Constrained Code Generation with Language Models](https://mlsanity.com/paper/2504.09246/) (2025)
- [On the Challenges and Opportunities in Generative AI](https://mlsanity.com/paper/2403.00025/) (2024)
- [StructuredRAG: JSON Response Formatting with Large Language Models](https://mlsanity.com/paper/2408.11061/) (2024)
- [Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling](https://mlsanity.com/paper/2504.05410/) (2025)
- [Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering](https://mlsanity.com/paper/2505.12025/) (2025)
- [Reliable Text-to-SQL with Adaptive Abstention](https://mlsanity.com/paper/2501.10858/) (2025)
- [SLOT: Structuring the Output of Large Language Models](https://mlsanity.com/paper/2505.04016/) (2025)
- [CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning](https://mlsanity.com/paper/2411.16313/) (2024)
- [Constrained Decoding of Diffusion LLMs with Context-Free Grammars](https://mlsanity.com/paper/2508.10111/) (2025)
- [Pie: A Programmable Serving System for Emerging LLM Applications](https://mlsanity.com/paper/2510.24051/) (2025)
- [SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs](https://mlsanity.com/paper/2506.04250/) (2025)
- [Decoupling Task-Solving and Output Formatting in LLM Generation](https://mlsanity.com/paper/2510.03595/) (2025)
- [Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry](https://mlsanity.com/paper/2411.15221/) (2024)
- [Breaking the Hourglass Phenomenon of Residual Quantization: Enhancing the Upper Bound of Generative Retrieval](https://mlsanity.com/paper/2407.21488/) (2024)
- [GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases](https://mlsanity.com/paper/2504.05478/) (2025)
- [Sampling from Your Language Model One Byte at a Time](https://mlsanity.com/paper/2506.14123/) (2025)
- [Empowering Healthcare Practitioners with Language Models: Structuring Speech Transcripts in Two Real-World Clinical Applications](https://mlsanity.com/paper/2507.05517/) (2025)
- [Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars](https://mlsanity.com/paper/2602.00612/) (2026)
- [Constrained Decoding with Speculative Lookaheads](https://mlsanity.com/paper/2412.10418/) (2024)
- [CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing](https://mlsanity.com/paper/2501.05255/) (2025)
- [A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data](https://mlsanity.com/paper/2601.17717/) (2026)
- [Neuro-Symbolic Synergy for World Modeling](https://mlsanity.com/paper/2602.10480/) (2026)

## Abstract (arXiv)

To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generation. However, as we show in this work, not only do such methods incur performance overhead during generation, but many of them also significantly impair task accuracy, if they do not correctly align the underlying LLM sub-word vocabularies with external constraints. To address this, we present a novel decoding algorithm, DOMINO, that can enforce constraints in a fully subword-aligned fashion, while leveraging pre-computation and speculative decoding to achieve virtually no overhead and in some cases even almost 2× speedup over unconstrained decoding -- thereby outperforming existing approaches by a wide margin.