Newest papers

Metamodel-Guided LLM Decoding for Consistent DSL Generation

Boqi Chen, Aren A. Babikian, Jose A. Lopez · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29749 · cited by 0 works (OpenAlex) · open-access PDF

Korean

그것은 LLDecistenined 효과적인 언어 모델 decistenined (LLMs)는 점점 더 도메인-특별 언어 (DSLs)로 작성 된 여섯 개의 제한된 디코딩 접근 방식으로 소프트웨어 엔지니어링 아티팩트를 생성하는 데 사용됩니다. 이 올바른 DSL 인스턴스는 일반적으로 구체적인 메타텍스뿐만 아니라 생성 된 텍스트를 통해 표현 된 제한 된 제한된 메타텍스뿐만 아니라 메타 모델 수준의 제한 일관성에 의해 정의 된 추상적 인 메타 모델에 의해 정의되어야합니다. 우리는 MeMoDecode를 제시합니다. 존재하는 제한된 디코딩 접근 방식은 일반적으로 DSL의 구체적인 합계, 추상적 합계 및 잘 형성 된 성능을 보장합니다.

Machine translation (Meta M2M100); the English original follows.

Abstract

Large language models (LLMs) are increasingly used to generate software engineering artifacts written in domain-specific languages (DSLs). Correct DSL instances usually must comply with not only the concrete syntax but also the abstract syntax defined by a metamodel augmented with semantic well-formedness constraints. Existing constrained decoding approaches typically guarantee compliance only with concrete syntax or with a limited set of semantic constraints expressed over the generated text, making metamodel-level constraint consistency difficult to enforce during generation. We present MeMoDecode: a decoding framework that enforces a DSL's concrete syntax, abstract syntax, and well-formedness constraints jointly. Specifically, whenever the LLM generates a complete metamodel concept, MeMoDecode incrementally maps the current output to a partial model and verifies whether it can still be completed into a consistent instance. We combine MeMoDecode with a simple retry mechanism that resumes decoding from the most recent completable snapshot whenever an inconsistency is detected. Under a sound backend verifier, MeMoDecode never performs worse than grammar-constrained decoding on alignment metrics satisfying natural assumptions. Across four DSLs and six open-weight LLMs ranging from 0.6B to 70B parameters, MeMoDecode achieves the highest consistency, improving consistency by 23% on average over unconstrained decoding and by 8% on average over grammar-constrained decoding. It also improves benchmark performance while incurring only modest runtime overhead. These results show that metamodel-guided decoding is an effective approach for enforcing DSL consistency during decoding across diverse DSLs and LLM scales.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Decoding methods, Digital subscriber line, Consistency (knowledge bases), Programming language, Syntax

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange