# DocCGen: Document-based Controlled Code Generation

arXiv: https://arxiv.org/abs/2406.11925 · HTML: https://mlsanity.com/paper/2406.11925/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 10 of 10)

- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction](https://mlsanity.com/paper/2112.01488/) (2021)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System](https://mlsanity.com/paper/1802.08979/) (2018)
- [When Language Model Meets Private Library](https://mlsanity.com/paper/2210.17236/) (2022)
- [Benchmarking and Improving Text-to-SQL Generation under Ambiguity](https://mlsanity.com/paper/2310.13659/) (2023)

## Built on by (most cited first, 11 of 11)

- [A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages](https://mlsanity.com/paper/2410.03981/) (2024)
- [A Mixture of Linear Corrections Generates Secure Code](https://mlsanity.com/paper/2507.09508/) (2025)
- [IaC Generation with LLMs: An Error Taxonomy and A Study on Configuration Knowledge Injection](https://mlsanity.com/paper/2512.14792/) (2025)
- [ConCodeEval: Evaluating Large Language Models for Code Constraints in Domain-Specific Languages](https://mlsanity.com/paper/2407.03387/) (2024)
- [Prompt engineering and framework: implementation to increase code reliability based guideline for LLMs](https://mlsanity.com/paper/2506.10989/) (2025)
- [ReproAgent: Contract-Guided Paper-to-Code Reproduction](https://mlsanity.com/paper/2608.24291/) (2026)
- [Natural Language Interaction with Databases on Edge Devices in the Internet of Battlefield Things](https://mlsanity.com/paper/2506.06396/) (2025)
- [CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language](https://mlsanity.com/paper/2603.14501/) (2026)
- [SmartHomeSecure: Automated Detection and Repair of Smart Home Configuration Errors Using Large Language Models](https://mlsanity.com/paper/2607.06748/) (2026)
- [PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language](https://mlsanity.com/paper/2607.09789/) (2026)
- [Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models](https://mlsanity.com/paper/2608.14797/) (2026)

## Abstract (arXiv)

Recent developments show that Large Language Models (LLMs) produce state-of-the-art performance on natural language (NL) to code generation for resource-rich general-purpose languages like C++, Java, and Python. However, their practical usage for structured domain-specific languages (DSLs) such as YAML, JSON is limited due to domain-specific schema, grammar, and customizations generally unseen by LLMs during pre-training. Efforts have been made to mitigate this challenge via in-context learning through relevant examples or by fine-tuning. However, it suffers from problems, such as limited DSL samples and prompt sensitivity but enterprises maintain good documentation of the DSLs. Therefore, we propose DocCGen, a framework that can leverage such rich knowledge by breaking the NL-to-Code generation task for structured code languages into a two-step process. First, it detects the correct libraries using the library documentation that best matches the NL query. Then, it utilizes schema rules extracted from the documentation of these libraries to constrain the decoding. We evaluate our framework for two complex structured languages, Ansible YAML and Bash command, consisting of two settings: Out-of-domain (OOD) and In-domain (ID). Our extensive experiments show that DocCGen consistently improves different-sized language models across all six evaluation metrics, reducing syntactic and semantic errors in structured code. We plan to open-source the datasets and code to motivate research in constrained code generation.