AI News HubLIVE
原文

The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models

This paper introduces 'constraint tax,' a metric for the accuracy loss caused by structured output constraints in small language models. Experiments show that enforcing schemas like JSON increases validity but reduces answer accuracy, advocating for a 'reason free, constrain late' approach. Production systems should report multiple metrics separately.

Article intelligence

EngineersAdvanced

Key points

  • Hard output constraints impose a 'constraint tax,' lowering answer accuracy for small models.
  • Experiments show schema validity rose from 61.5% to 100%, but answer accuracy fell from 19.7% to 11.0%.
  • Wrong-valid-schema outputs increased from 49.5% to 88.9%.
  • Recommends a 'reason free, constrain late' design pattern and separate reporting of metrics.

Why it matters

This matters because hard output constraints impose a 'constraint tax,' lowering answer accuracy for small models.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.26128] The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models

[Submitted on 20 May 2026]

Title:The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models

View a PDF of the paper titled The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models, by Jaideep Ray

View PDF HTML (experimental)

Abstract:Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This paper targets on-device and low-cost small language model (SLM) deployments, where sub-3B models are attractive for privacy, latency, and commodity hardware but have limited capacity to satisfy schemas while solving tasks. The usual engineering assumption is that hard output constraints improve reliability without changing the underlying answer. We show that this assumption is unsafe for small models. We introduce \emph{constraint tax}, a measurement protocol for isolating the answer and executable-accuracy loss caused by structured-output constraints at fixed model, fixed task distribution, and fixed problem instances. Across 15,000 commodity-GPU generations with Qwen2.5-0.5B, Qwen2.5-1.5B, and SmolLM2-1.7B, hard answer-only schema decoding raises schema validity from 61.5\% to 100.0\%, but lowers answer accuracy from 19.7\% to 11.0\% and increases wrong-valid-schema outputs from 49.5\% to 88.9\%. The strongest industry analogue is a deterministic calendar tool-call task: Qwen2.5-1.5B achieves 91.5\% executable accuracy with prompt-only JSON but only 48.0\% under the same hard tool-call schema, while both modes are 100.0\% schema-valid. The error is semantic, not structural. We also show that the 3B boundary still pays a direct-schema tax and that delayed packaging supports a constructive design pattern: reason free, constrain late. The practical conclusion is direct: production systems should report schema validity, answer accuracy, executable accuracy, and wrong-valid-schema rate separately.

Subjects:

Machine Learning (cs.LG); Software Engineering (cs.SE)

Cite as: arXiv:2605.26128 [cs.LG]

(or arXiv:2605.26128v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.26128

arXiv-issued DOI via DataCite

Submission history

From: Jaideep Ray [view email] [v1] Wed, 20 May 2026 07:11:32 UTC (1,423 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models, by Jaideep Ray

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-05

Change to browse by:

cs cs.SE

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)