# Leveraging LLMs for Multi-File DSL Code Generation: An Industrial Case Study

arXiv: https://arxiv.org/abs/2604.24678 · HTML: https://mlsanity.com/paper/2604.24678/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 28 of 28)

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation](https://mlsanity.com/paper/2305.16938/) (2023)
- [Abstract Syntax Networks for Code Generation and Semantic Parsing](https://mlsanity.com/paper/1704.07535/) (2017)
- [A Practical Survey on Zero-shot Prompt Design for In-context Learning](https://mlsanity.com/paper/2309.13205/) (2023)
- [On the Effectiveness of Large Language Models in Domain-Specific Code Generation](https://mlsanity.com/paper/2312.01639/) (2023)
- [A Survey on Evaluating Large Language Models in Code Generation Tasks](https://mlsanity.com/paper/2408.16498/) (2024)
- [Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review](https://mlsanity.com/paper/2406.12655/) (2024)
- [A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation](https://mlsanity.com/paper/2407.02742/) (2024)
- [Layered gradient accumulation and modular pipeline parallelism: fast and efficient training of large language models](https://mlsanity.com/paper/2106.02679/) (2021)
- [PLoRA: Efficient Concurrent LoRA Training for Large Language Models](https://mlsanity.com/paper/2508.02932/) (2025)
- [Guiding Large Language Models to Generate Computer-Parsable Content](https://mlsanity.com/paper/2404.05499/) (2024)
- [Development and Evolution of Xtext-based DSLs on GitHub: An Empirical Investigation](https://mlsanity.com/paper/2501.19222/) (2025)

## Abstract (arXiv)

Large language models (LLMs) perform strongly on general-purpose code generation, yet their applicability to enterprise domain-specific languages (DSLs) remains underexplored, especially for repository-scale change generation spanning multiple files and folder structures from a single natural-language (NL) instruction. We report an industrial case study at BMW that adapts code-oriented LLMs to generate and modify project-root DSL artifacts for an Xtext-based DSL that drives downstream Java/TypeScript code generation. We develop an end-to-end pipeline for dataset construction, multi-file task representation, model adaptation, and evaluation. We encode DSL folder hierarchies as structured, path-preserving JSON, allowing single-response generation at repository scale and learning cross-file dependencies. We evaluate two instruction-tuned code LLMs (Qwen2.5-Coder and DeepSeek-Coder, 7B) under three configurations: baseline prompting, one-shot in-context learning, and parameter-efficient fine-tuning (QLoRA). Beyond standard similarity metrics, we introduce task-specific measures that assess edit correctness and repository structural fidelity. Fine-tuning yields the most significant gains across models and metrics, achieving high exact-match accuracy, substantial edit similarity, and structural fidelity of 1.00 on our held-out set for multi-file outputs. At the same time, one-shot in-context learning provides smaller but consistent improvements over baseline prompting. We further validate practical utility via an expert developer survey and an execution-based check using the existing code generator.