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

Spanish

Los modelos de descifrado de idiomas de gran alcance (LLMs) se utilizan cada vez más para generar artefactos de ingeniería de software en gramos escritos en idiomas específicos de dominio (DSLs). Estas instancias de DSL correctas generalmente deben cumplir no solo con la sintaxis concreta, sino también con la sintaxis abstracta definida por un metamodel de nivel de restricción improvisado con restricciones de bienformación semántica. Presentamos MeMoDecode: un marco de descifrado que exige el cumplimiento de la sintaxis concreta de DSL, la sintaxis abstracta y el descifrado de AcSL generalmente con un conjunto limitado de restricciones semánticas expresadas en el texto generado, lo que dificulta la aplicación de la coherencia de la

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