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

• URL: http://arxiv.org/abs/2605.26128v1
• Date: Wed, 20 May 2026 07:11:32 GMT
• Title: The Constraint Tax: Measuring Validity-Correctness Tradeoffs in Structured Outputs for Small Language Models
• Abstract summary: This paper targets on-device and low-cost small language model (SLM) deployments.<n>We show that hard output constraints improve reliability without changing the underlying answer.<n>We introduce emphconstraint tax, a measurement protocol for isolating the answer and executable-accuracy loss.
• Score: 0.5482532589225553
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training [66.72708893922605]
  Post-training of large multimodal models should add new capabilities while preserving those from pre-training.<n>SFT gives explicit target supervision that learns a task from near-zero accuracy, but its off-policy targets move the model far enough to cause forgetting.<n>We introduce ReDraft, which obtains both from the model's own failures.
  arXiv  Detail & Related papers  (2026-09-15T04:59:03Z)
• Beyond Fluent Generation: A CPU Reliability Benchmark for MCP-Style Tool Calling in Sub-2B Small Language Models for Edge Deployment [0.0]
  Resource constrained single-board computers including Raspberry Pi, NVIDIA Jetson Nano, Arduino UNO Q, Orange Pi, and LattePanda motivate on-device small language model (SLM) agents.<n>Model Context Protocol (MCP)-style tool invocation demands more than fluent generation.
  arXiv  Detail & Related papers  (2026-09-07T11:44:38Z)
• Joint Optimization of Tool Creation and Use for Large Language Model Agents [69.07066297088187]
  SMITH (-grounded Multi-task Iterative Tool Honing) trains tool creation and tool use inside a single policy.<n>A 4B Qwen3 trained with SMITH on 13 procedural reasoning tasks with exact verifiers reaches 79.8 macro-average accuracy on held-out tasks.<n>It also reaches 40.4 on TabMWP-Hard and 42.6 on out-of-domain GQA (+7.6 over the best same-backbone inference-time baseline)
  arXiv  Detail & Related papers  (2026-08-25T13:59:34Z)
• DRL: A Deterministic Relational Middleware Layer for Transaction-Safe Enterprise NL2SQL Under Schema-Graph Scaling [0.19116784879310023]
  Deploying natural-language interfaces over enterprise O fails scale because schemagraph fails to scale at scale.<n>We present DRL, a safe pipeline interposing between front-ends backends.<n>We evaluate DRL onop, a 1,000 scaling model, and an enterprise schema-linked NL2 taxonomy.<n>GPT-4o, Claude Sonnet 4.5, and Gemini 2.5 Flash achieve 52.9%, 54.5%, and 52.1% execution match under a corrected evaluation harness.
  arXiv  Detail & Related papers  (2026-07-23T18:01:11Z)
• Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata [57.27430779838529]
  We present an exact and tractable algorithm for sampling from the constrained mean-field posterior under any constraint expressible as a finite automaton.<n>The approach guarantees constraint satisfaction by construction, supports both greedy and sampling-based decoding, and is compatible with parallel and block-wise decoding.<n> Empirical evaluations on Dream-7B and LLaDA-8 show substantial accuracy gains across various tasks.
  arXiv  Detail & Related papers  (2026-07-08T05:48:57Z)
• Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving [69.5155152169752]
  We propose a two-stage cascaded solution for large language models (LLMs)<n>Stage 1 clusters incoming queries and assigns each cluster to its most cost-effective model.<n>Stage 2 adds a quality estimation (QE) cascade; when an output from Stage 1 is judged low-quality, the query is escalated to a stronger model.<n>On the test datasets, the cascaded system retains 97-99% of the strongest model's accuracy while reducing Time Per Output Token (TPOT)<n>It requires only task-correctness labels and adapts to changes in the model pool without manual reconfiguration.
  arXiv  Detail & Related papers  (2026-06-25T18:29:24Z)
• Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization [54.749573452394664]
  We find that accuracy collapses as instance data grows, even when the formulation itself is simple.<n>We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data rather than from prompt prompt.<n>We validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories.
  arXiv  Detail & Related papers  (2026-05-20T21:25:41Z)
• TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments [0.0]
  Production agent frameworks transmit tool schemas as MCP, a format designed for machine parsing, not for interpretation by language models.<n>For small models (4B-14B), this protocol mismatch accounts for the majority of tool-use failure at production sizes.<n>We present TSCG, a deterministic tool-schema compiler that resolves this mismatch at the API boundary.
  arXiv  Detail & Related papers  (2026-05-04T15:35:45Z)
• When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models [2.064923532131528]
  Deployed language models must produce outputs that are both correct and format-compliant.<n>We study this structured-output reliability gap using two mathematical benchmarks -- GSM8K and MATH.<n>We develop AloLab, an iterative system-prompt requiring only black-box API access to the target model.
  arXiv  Detail & Related papers  (2026-05-04T09:07:44Z)
• Tool Attention Is All You Need: Dynamic Tool Gating and Lazy Schema Loading for Eliminating the MCP/Tools Tax in Scalable Agentic Workflows [2.2228811750157482]
  We introduce Tool Attention, a scalable-layer mechanism that generalizes the "Attention Is All You Need" paradigm.<n>We evaluate on a simulated 120-tool, six-server benchmark whose per-server token counts are calibrated to public audits of real MCP deployments.<n>Tool Attention directly reduces measured per-turn tool tokens by 95.0% (47.3k -> 2.4k) and raises effective context utilization (a token-ratio quantity) from 24% to 91%.
  arXiv  Detail & Related papers  (2026-04-23T16:10:00Z)
• Did You Forget What I Asked? Prospective Memory Failures in Large Language Models [0.0]
  Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks.<n>We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled paradigm.<n>Vulnerability is highly type-dependent, with drops up to 50%, while avoidance constraints remain comparatively robust.<n>A salience-enhanced format (explicit instruction framing plus a trailing reminder) recovers much of the lost compliance, restoring performance to 90-100% in many settings.
  arXiv  Detail & Related papers  (2026-03-07T05:58:19Z)
• PromptPort: A Reliability Layer for Cross-Model Structured Extraction [0.11280931253550518]
  Structured extraction with LLMs fails in production not because models lack understanding, but because output formatting is unreliable across models and prompts.<n>We present PromptPort, a reliability layer combining deterministic canonicalization with a lightweight verifier (DistilBERT) and a safe-override policy.<n>The method generalizes to held-out model families and provides explicit abstention when uncertain, enabling reliable structured extraction in production deployments.
  arXiv  Detail & Related papers  (2026-01-06T03:54:27Z)
• AdapTrack: Constrained Decoding without Distorting LLM's Output Intent [53.75852524070165]
  Language model-based code generation and completion tools can sometimes produce code that does not meet necessary constraints.<n> Constrained decoding techniques are developed to help the model generate code adhering to the constraints.<n>AdapTrack avoids distorting the output intent of the model, thereby producing results that are not only constraint-compliant but also semantically aligned with model's output intent.
  arXiv  Detail & Related papers  (2025-10-20T10:11:34Z)
• Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production [55.76222360698305]
  We explore a class of supervised training objectives that allow a language model to dynamically and autonomously scale the number of compute steps used for each input token.<n>For any token, the model can request additional compute steps by emitting a don't know> output.<n>We find that the CYB model requests additional steps when doing so improves accuracy, and the model adapts its processing time to token-level complexity and context.
  arXiv  Detail & Related papers  (2025-10-13T21:07:05Z)
• LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! [53.84130385074551]
  Large reasoning models (LRMs) tackle complex reasoning problems by following long chain-of-thoughts (Long CoT)<n>We find that a Large Language model (LLM) can effectively learn Long CoT reasoning through data-efficient supervised fine-tuning (SFT) and parameter-efficient low-rank adaptation (LoRA)<n>With just 17k long CoT training samples, the Qwen2.5-32B-Instruct model achieves significant improvements on a wide range of math and coding benchmarks.
  arXiv  Detail & Related papers  (2025-02-11T08:48:48Z)
• Gradient-Free Structured Pruning with Unlabeled Data [57.999191898036706]
  We propose a gradient-free structured pruning framework that uses only unlabeled data. Up to 40% of the original FLOP count can be reduced with less than a 4% accuracy loss across all tasks considered.
  arXiv  Detail & Related papers  (2023-03-07T19:12:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.