Does Structured Intent Representation Generalize? A Cross-Language, Cross-Model Empirical Study of 5W3H Prompting

TL;DR

This study evaluates the generalization of structured 5W3H intent prompts across multiple languages and models, demonstrating AI-assisted expansion maintains goal alignment and reduces output variance, enhancing cross-language and cross-model robustness.

Contribution

It extends prior Chinese-only research by including English and Japanese, and investigates AI-assisted prompt expansion and cross-model consistency in a comprehensive empirical study.

Findings

AI-expanded 5W3H prompts match manual prompts in goal alignment

Structured prompts reduce cross-model output variance in some cases

Unstructured prompts show bias with inflated scores and variance

Abstract

Does structured intent representation generalize across languages and models? We study PPS (Prompt Protocol Specification), a 5W3H-based framework for structured intent representation in human-AI interaction, and extend prior Chinese-only evidence along three dimensions: two additional languages (English and Japanese), a fourth condition in which a user's simple prompt is automatically expanded into a full 5W3H specification by an AI-assisted authoring interface, and a new research question on cross-model output consistency. Across 2,160 model outputs (3 languages x 4 conditions x 3 LLMs x 60 tasks), we find that AI-expanded 5W3H prompts (Condition D) show no statistically significant difference in goal alignment from manually crafted 5W3H prompts (Condition C) across all three languages, while requiring only a single-sentence input from the user. Structured PPS conditions often reduce or reshape cross-model output variance, though this effect is not uniform across languages and metrics; the strongest evidence comes from identifying spurious low variance in unconstrained baselines. We also show that unstructured prompts exhibit a systematic dual-inflation bias: artificially high composite scores and artificially low apparent cross-model variance. These findings suggest that structured 5W3H representations can improve intent alignment and accessibility across languages and models, especially when AI-assisted authoring lowers the barrier for non-expert users.