StructureBench: A Unified Benchmark Suite for Multi-Scenario Structured Generation Tasks with On-Device Models

摘要

Structured output generation is increasingly critical for real-world AI systems, particularly in on-device settings where small language models (0.5B–8B parameters) must produce machine-executable outputs under strict latency and privacy constraints. Although constrained decoding provides formal guarantees of structural validity without retraining, its effectiveness across different tasks, models, and constraint formalisms remains insufficiently understood. We introduce StructureBench, a comprehensive benchmark for structured generation on edge devices, covering JSON and tool-call generation, code synthesis, mathematics, science, and domain-specific languages, and evaluating over 11 on-device language and vision–language models spanning 0.5B–8B parameters. StructureBench systematically compares prompt-based generation with three widely used constrained decoding frameworks—Outlines, XGrammar, and Guidance—and adopts decoupled metrics to separately assess structural validity and semantic correctness. Our experiments show that constrained decoding consistently enforces syntactic validity, but does not reliably improve semantic accuracy and may even degrade performance for smaller models or complex grammars. These findings reveal clear task- and model-dependent boundaries for effective constrained decoding and highlight the need for scenario-aware adaptation in on-device structured generation. We release StructureBench at https://github.com/Str-Ben/StructureBench.