Structured Intent as a Protocol-Like Communication Layer: Cross-Model Robustness, Framework Comparison, and the Weak-Model Compensation Effect

TL;DR

This paper demonstrates that structured intent representations, specifically the 5W3H framework, enhance cross-model robustness, reduce goal variance across languages, and improve user interaction efficiency in human-AI communication.

Contribution

It extends prior work by evaluating structured prompts across multiple models, languages, and domains, and compares them with other frameworks, showing their effectiveness and robustness.

Findings

Structured prompts significantly reduce cross-language goal variance.

Weak-models benefit more from structured prompts, showing a larger performance gain.

User study shows 60% fewer interaction rounds and higher satisfaction with structured prompts.

Abstract

How reliably can structured intent representations preserve user goals across different AI models, languages, and prompting frameworks? Prior work showed that PPS (Prompt Protocol Specification), a 5W3H-based structured intent framework, improves goal alignment in Chinese and generalizes to English and Japanese. This paper extends that line of inquiry in three directions: cross-model robustness across Claude, GPT-4o, and Gemini 2.5 Pro; controlled comparison with CO-STAR and RISEN; and a user study (N=50) of AI-assisted intent expansion in ecologically valid settings. Across 3,240 model outputs (3 languages x 6 conditions x 3 models x 3 domains x 20 tasks), evaluated by an independent judge (DeepSeek-V3), we find that structured prompting substantially reduces cross-language score variance relative to unstructured baselines. The strongest structured conditions reduce cross-language sigma from 0.470 to about 0.020. We also observe a weak-model compensation pattern: the lowest-baseline model (Gemini) shows a much larger D-A gain (+1.006) than the strongest model (Claude, +0.217). Under the current evaluation resolution, 5W3H, CO-STAR, and RISEN achieve similarly high goal-alignment scores, suggesting that dimensional decomposition itself is an important active ingredient. In the user study, AI-expanded 5W3H prompts reduce interaction rounds by 60 percent and increase user satisfaction from 3.16 to 4.04. These findings support the practical value of structured intent representation as a robust, protocol-like communication layer for human-AI interaction.