自然语言声明式提示（NLD-P）：一种模块化治理方法，用于在模型漂移下的提示设计
Natural Language Declarative Prompting (NLD-P): A Modular Governance Method for Prompt Design Under Model Drift
AI总结：
本文提出NLD-P作为模块化治理方法，通过自然语言声明式提示解决模型漂移下的提示设计问题，提供可解释的控制框架。
摘要：
大语言模型（LLMs）的快速演进将提示工程从局部技艺转变为系统层面的治理挑战。随着模型在不同世代中扩展和更新，提示行为对指令遵循政策、对齐制度和解码策略的变化变得敏感，这种现象我们称为GPT规模模型漂移。在这种情况下，表面的格式规范和随意的优化不足以确保稳定、可解释的控制。本文重新概念化自然语言声明式提示（NLD-P）为一种声明式治理方法，而不是刚性的字段模板。NLD-P被形式化为一种模块化控制抽象，将来源、约束逻辑、任务内容和生成后评估分开，直接用自然语言编码，不依赖外部协调代码。我们定义了最小合规标准，分析了模型依赖的模式接受性，并将NLD-P定位为一种可访问的治理框架，供在不断演进的LLM生态系统中操作的非开发者从业者使用。部分起草和编辑优化使用了在NLD-P下配置的模式绑定LLM助手。所有概念框架、方法论主张和最终修订均通过文档化的“人机协同”协议由人类作者指导、审查和批准。本文最后概述了在持续模型演进下的声明式控制的影响，并指明了未来经验验证的方向。
英文摘要：
The rapid evolution of large language models (LLMs) has transformed prompt engineering from a localized craft into a systems-level governance challenge. As models scale and update across generations, prompt behavior becomes sensitive to shifts in instruction-following policies, alignment regimes, and decoding strategies, a phenomenon we characterize as GPT-scale model drift. Under such conditions, surface-level formatting conventions and ad hoc refinement are insufficient to ensure stable, interpretable control. This paper reconceptualizes Natural Language Declarative Prompting (NLD-P) as a declarative governance method rather than a rigid field template. NLD-P is formalized as a modular control abstraction that separates provenance, constraint logic, task content, and post-generation evaluation, encoded directly in natural language without reliance on external orchestration code. We define minimal compliance criteria, analyze model-dependent schema receptivity, and position NLD-P as an accessible governance framework for non-developer practitioners operating within evolving LLM ecosystems. Portions of drafting and editorial refinement employed a schema-bound LLM assistant configured under NLD-P. All conceptual framing, methodological claims, and final revisions were directed, reviewed, and approved by the human author under a documented human-in-the-loop protocol. The paper concludes by outlining implications for declarative control under ongoing model evolution and identifying directions for future empirical validation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
