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

• URL: http://arxiv.org/abs/2604.24678v1
• Date: Mon, 27 Apr 2026 16:38:01 GMT
• Title: Leveraging LLMs for Multi-File DSL Code Generation: An Industrial Case Study
• Abstract summary: Large language models (LLMs) perform strongly on general-purpose code generation, yet their applicability to enterprise domain-specific languages (s) remains underexplored.<n>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.<n>We encode as structured, path-response generation at repository scale and learning cross-file dependencies.
• Score: 39.936784974007644
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models [54.53236295237077]
  We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning.<n> Output Prediction measures fine-grained, stateful execution reasoning across files.<n>Call Chain Prediction evaluates high-level architectural dependency understanding under noisy context.
  arXiv  Detail & Related papers  (2026-07-28T17:12:41Z)
• RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices [54.956760584923295]
  Researchers have made substantial progress using Large Language Models (LLMs) for code generation.<n>However, developers typically write code based on structured designs or specifications rather than raw natural language descriptions.<n>This gap between existing benchmarks and real industry development practices means that current benchmark scores may not accurately reflect how much code generation can help automate development tasks.
  arXiv  Detail & Related papers  (2026-04-24T15:35:54Z)
• Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering [4.120344028676837]
  Large Language Models (LLMs) have shown impressive capabilities across software engineering tasks, including question answering (QA)<n>We introduce StackRepoQA, the first multi-project, repository-level question answering dataset constructed from 1,318 real developer questions and accepted answers across 134 open-source Java projects.
  arXiv  Detail & Related papers  (2026-03-27T16:30:54Z)
• Do Not Treat Code as Natural Language: Implications for Repository-Level Code Generation and Beyond [13.550121154853715]
  We present Hydra, a repository-level code generation framework that treats code as structured code rather than natural language.<n>We show that Hydra achieves state-of-the-art performance across open- and closed-source CodeLLMs.
  arXiv  Detail & Related papers  (2026-02-12T07:44:00Z)
• IFEvalCode: Controlled Code Generation [69.28317223249358]
  The paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs.<n>The authors present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages.
  arXiv  Detail & Related papers  (2025-07-30T08:08:48Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• DependEval: Benchmarking LLMs for Repository Dependency Understanding [16.19185341217556]
  Large language models (LLMs) have shown considerable promise in code generation, real-world software development demands advanced repository-level reasoning.<n>We introduce a hierarchical benchmark designed to evaluate repository dependency understanding (DependEval)<n> Benchmark is based on 15,576 repositories collected from real-world websites.
  arXiv  Detail & Related papers  (2025-03-09T16:45:22Z)
• ExecRepoBench: Multi-level Executable Code Completion Evaluation [45.963424627710765]
  We introduce a novel framework for enhancing code completion in software development through the creation of a repository-level benchmark ExecRepoBench.<n>We present a multi-level grammar-based completion methodology conditioned on the abstract syntax tree to mask code fragments at various logical units.<n>Then, we fine-tune the open-source LLM with 7B parameters on Repo-Instruct to produce a strong code completion baseline model Qwen2.5-Coder-Instruct-C.
  arXiv  Detail & Related papers  (2024-12-16T17:14:35Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• DocCGen: Document-based Controlled Code Generation [33.19206322891497]
  DocCGen is a framework that can leverage rich knowledge by breaking the NL-to-Code generation task for structured code languages into a two-step process. Our experiments show that DocCGen consistently improves different-sized language models across all six evaluation metrics.
  arXiv  Detail & Related papers  (2024-06-17T08:34:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.