# The Alignment Problem in Constrained Code Generation

arXiv: https://arxiv.org/abs/2606.21619 · HTML: https://mlsanity.com/paper/2606.21619/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 41 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [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)
- [An Empirical Study of the Non-determinism of ChatGPT in Code Generation](https://mlsanity.com/paper/2308.02828/) (2023)
- [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)
- [Type-Constrained Code Generation with Language Models](https://mlsanity.com/paper/2504.09246/) (2025)
- [ChopChop: a Programmable Framework for Semantically Constraining the Output of Language Models](https://mlsanity.com/paper/2509.00360/) (2025)
- [Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective](https://mlsanity.com/paper/2506.05754/) (2025)
- [Constrained Decoding of Diffusion LLMs with Context-Free Grammars](https://mlsanity.com/paper/2508.10111/) (2025)
- [PyTy: Repairing Static Type Errors in Python](https://mlsanity.com/paper/2401.06619/) (2024)
- [Enhancing Code Generation for Low-Resource Languages: No Silver Bullet](https://mlsanity.com/paper/2501.19085/) (2025)
- [Assessing Small Language Models for Code Generation: An Empirical Study with Benchmarks](https://mlsanity.com/paper/2507.03160/) (2025)
- [LLM-Based Repair of Static Nullability Errors](https://mlsanity.com/paper/2507.20674/) (2025)
- [Union and intersection contracts are hard, actually](https://mlsanity.com/paper/2106.06278/) (2021)

## Built on by (most cited first, 1 of 1)

- [GrammarRL: Effective Grammar-Constrained Decoding via Reinforcement Learning](https://mlsanity.com/paper/2609.39869/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated strong capabilities in code generation, but their outputs frequently contain syntax or type errors that result in compilation failures. Constrained decoding has been proposed as a solution to mitigate compilation errors by construction, improving functional correctness as a byproduct. However, previous works overlook a critical aspect of constrained decoding: the alignment between constrainer (e.g., types), language model and the target specification language (e.g., TypeScript). Misalignment is caused by the constrainer being incomplete--rejecting programs that belong to the target--or unsound--allowing programs that are not part of the target. The bias created by incompleteness distorts the language model distribution, and can be detrimental for code generation. We evaluate this hypothesis using seven language models, two target languages, two constrainers, enforcing types and syntax during decoding, and we study how language models react to varying levels of incompleteness. On three benchmarks, when the constrainer is incomplete, unconstrained decoding significantly outperforms constrained decoding in terms of functional correctness. Incompleteness pushes the model into low-probability regions of the program space, causing the generation to frequently time out, and reducing functional correctness by up to 97%. These contributions make the community aware of the negative effects of misalignment in constrained decoding, and provide quantitative insights on how to design constrainers that are beneficial for code generation systems with formal guarantees.