Compact Constraint Encoding for LLM Code Generation: An Empirical Study of Token Economics and Constraint Compliance

TL;DR

This study evaluates whether compact, structured constraint headers can reduce token usage in LLM code generation prompts without affecting constraint compliance, finding significant token savings but no impact on compliance rates.

Contribution

It demonstrates that compact constraint encoding reduces token consumption substantially without degrading constraint satisfaction across multiple models and tasks.

Findings

Compact headers cut constraint tokens by ~71%.

No significant difference in constraint satisfaction rate across encoding forms.

Model self-assessments overestimate actual compliance.

Abstract

LLMs used for code generation are typically guided by engineering constraints--technology choices, dependency restrictions, and architectural patterns--expressed in verbose natural language. We investigate whether compact, structured constraint headers can reduce prompt token consumption without degrading constraint compliance. Across six experimental rounds spanning 11 models, 16 benchmark tasks, and over 830 LLM invocations, we find that compact headers reduce constraint-portion tokens by approximately 71% and full-prompt tokens by 25--30%, replicated across three independent rounds. However, we detect no statistically significant differences in constraint satisfaction rate (CSR) across three encoding forms or four propagation modes; observed effect sizes are negligible (Cliff's $\delta$ < 0.01, 95% CI spanning $\pm$2.6 percentage points). This null pattern holds across two models from different capability tiers. A supplementary experiment with four non-CSS tasks provides additional cross-domain support for the encoding null result. The largest observed sources of compliance variance are constraint type ($\Delta$ = 9 percentage points between normal and counter-intuitive constraints) and task domain: counter-intuitive constraints opposing model defaults fail at 10--100%, while conventional constraints achieve 99%+ compliance regardless of encoding. Model self-assessments systematically overestimate compliance relative to rule-based scoring, revealing a gap between constraint understanding and execution. Under the tested conditions, the primary benefit of compact constraint encoding is token reduction rather than compliance improvement, and engineering effort toward compliance is better directed at constraint design than prompt formatting.