Research

Paper

AI LLM March 19, 2026

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

Authors

Peng Gang

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.

Metadata

arXiv ID: 2603.18976
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-19
Fetched: 2026-03-20 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.18976v1</id>\n    <title>Evaluating 5W3H Structured Prompting for Intent Alignment in Human-AI Interaction</title>\n    <updated>2026-03-19T14:41:06Z</updated>\n    <link href='https://arxiv.org/abs/2603.18976v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.18976v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-19T14:41:06Z</published>\n    <arxiv:comment>27 pages, figures, tables, and appendix. Primary category: human-computer interaction / human-AI interaction. Public artifact repository and implementation resources are referenced in the manuscript</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Peng Gang</name>\n    </author>\n  </entry>"
}