Evaluating 5W3H Structured Prompting for Intent Alignment in Human-AI Interaction

TL;DR

This study evaluates a structured 5W3H prompt framework (PPS) for improving intent communication in human-AI interaction, demonstrating its effectiveness in enhancing goal alignment and reducing follow-up prompts across various tasks and models.

Contribution

It introduces the PPS framework based on 5W3H for structured intent representation and provides empirical evidence of its benefits over simple prompts in diverse domains and models.

Findings

Rendered PPS improves goal alignment compared to simple prompts and raw JSON.

Structured prompts reduce follow-up interactions by approximately 66%.

Effectiveness of PPS varies with task ambiguity, being more beneficial in high-ambiguity tasks.

Abstract

Natural language prompts often suffer from intent transmission loss: the gap between what users actually need and what they communicate to AI systems. We evaluate PPS (Prompt Protocol Specification), a 5W3H-based framework for structured intent representation in human-AI interaction. In a controlled three-condition study across 60 tasks in three domains (business, technical, and travel), three large language models (DeepSeek-V3, Qwen-Max, and Kimi), and three prompt conditions - (A) simple prompts, (B) raw PPS JSON, and (C) natural-language-rendered PPS - we collect 540 AI-generated outputs evaluated by an LLM judge. We introduce goal_alignment, a user-intent-centered evaluation dimension, and find that rendered PPS outperforms both simple prompts and raw JSON on this metric. PPS gains are task-dependent: gains are large in high-ambiguity business analysis tasks but reverse in low-ambiguity travel planning. We also identify a measurement asymmetry in standard LLM evaluation, where unconstrained prompts can inflate constraint adherence scores and mask the practical value of structured prompting. A preliminary retrospective survey (N = 20) further suggests a 66.1% reduction in follow-up prompts required, from 3.33 to 1.13 rounds. These findings suggest that structured intent representations can improve alignment and usability in human-AI interaction, especially in tasks where user intent is inherently ambiguous.