Empirical Study for Structured Output Control in LLMs for Software Engineering
2026-06-08 • Software Engineering
Software Engineering
AI summaryⓘ
The authors explain that when large language models (LLMs) generate code or other outputs for software engineering, these outputs have to fit strict formats to work properly in real systems. They found that while tools can reduce simple syntax mistakes, many structural and meaning-related errors still happen, causing problems downstream. Their study shows that current fixes aren't enough and suggests the need for methods that ensure both the format and the content are correct. This is important because even if an output looks right, if it doesn't exactly follow the expected structure, it won't work in practice.
Large Language ModelsSoftware EngineeringStructural FidelitySyntax ErrorsSemantic ErrorsGrammar-Constrained DecodingRegex ValidationTemplate Token Match GenerationAutoregressive DecodingData Pipelines
Authors
Yewei Song, Prateek Rajput, Tiezhu Sun, Saad Ezzini, Tegawendé F. Bissyandé, Jacques Klein
Abstract
LLM-generated outputs in software engineering rarely exist in isolation. They must plug into toolchains, APIs, and data pipelines that impose strict, often organization-specific structural contracts. A semantically correct output that violates the expected format is, from the consuming system's perspective, indistinguishable from a wrong answer, making structural fidelity an operational prerequisite for deploying LLMs in practice. Yet current models routinely produce syntactically invalid or structurally non-compliant outputs. Unlike encoders, autoregressive decoders generate text token-by-token with a local rather than global focus, amplifying structural fragility whenever the target format deviates from familiar training distributions. We present a systematic evaluation of structural reliability across four representative SE tasks, categorizing failures into syntax, structural, and semantic errors. We benchmark ways of mitigation targeting the decoder: grammar-constrained decoding, regex-based validation, and a strict template-driven control (Template Token Match Generation, TTMG) to isolate the sources of these failures. TTMG nearly eliminates syntax errors, yet substantial structural and semantic errors persist, demonstrating that the core bottleneck lies beyond syntax formatting. A detailed case study further illustrates how residual errors cascade in downstream workflows. Our findings show that current structure-enforcing tools are necessary but insufficient, and highlight the need for approaches that jointly ensure structural fidelity and semantic correctness in LLM-driven workflows.