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

Russian

В процессе расшифровки больших языков эффективные модели расшифровки (LLM) все чаще используются для генерирования артефактов семантической хорошо сформированности программного обеспечения, написанных на шести языках, специфических для домена (DSL). Эти правильные инстанции DSL обычно должны соответствовать не только конкретному синтаксису, но и абстрактной синтаксису, определяемому на уровне метамодела, усиливаемой с ограничениями семантической хорошо сформированности. Мы представляем MeMoDecode: рамки расшифровки, которые обычно обеспечивают соответствие конкретному синтаксису, абстрактному синтаксису и хорошо сформированной производительности DSL, в то время как AcSL ограничивает выполнение совместно с ограниченным набором семантических ограничений, выражен

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