Natural Language Declarative Prompting (NLD-P): A Modular Governance Method for Prompt Design Under Model Drift
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910033798758400 |
|---|---|
| author | Kim, Hyunwoo Yi, Hanau Bae, Jaehee Kim, Yumin |
| author_facet | Kim, Hyunwoo Yi, Hanau Bae, Jaehee Kim, Yumin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22790 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Natural Language Declarative Prompting (NLD-P): A Modular Governance Method for Prompt Design Under Model Drift Kim, Hyunwoo Yi, Hanau Bae, Jaehee Kim, Yumin Computation and Language Artificial Intelligence 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. |
| title | Natural Language Declarative Prompting (NLD-P): A Modular Governance Method for Prompt Design Under Model Drift |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.22790 |