Use structured, human-in-the-loop prompting governance (such as NLD-P) with systematic human review to preserve authorship boundaries in AI-assisted research¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article discloses a human–AI collaborative methodology in which LLMs served only as assistive tools under "a human-in-the-loop, human-in-control, and human-as-final-author model of collaboration." Prompts were formulated as modular, human-readable instructions using the Natural Language Declarative Prompting (NLD-P) framework to constrain task structure, output scope, and revision criteria, and all outputs were subject to systematic human review, verification, and selective integration.

Design Implications¶

Context¶

Requirements¶

• Structured prompting methodology enforcing constraints on task structure, output scope, and revision criteria
• Systematic human review, verification, and selective integration of all LLM outputs

Constraints¶

• Applied in this study to maintain role clarity, not to extend or generalize the prompting framework itself

Target Learners¶

• Researchers using LLMs in scholarly writing

Target Learning Goals¶

• Transparent reporting of AI assistance and preservation of human epistemic responsibility

Related Strategies¶

• Use an AI-assisted vibe coding workflow with human pedagogical control to move educational tools from idea to classroom within days

Examples¶

-

Key Sources¶

• Hyunwoo Kim, Harin Yu, Hanau Yi. (2026). The LLM Fallacy: Misattribution in AI-Assisted Cognitive Workflows. https://arxiv.org/abs/2604.14807