发表机构
UIUC University of Illinois Urbana-Champaign; KTH Royal Institute of Technology（伊利诺伊大学厄巴纳-香槟分校; 瑞典皇家理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对提示设计缺乏系统性的问题，提出提示最小化方法，在保持输出保真度下缩减提示长度，减少计算开销并提升推理性能，为高效提示工程开辟新方向。
AI 中文摘要
尽管大型语言模型（LLMs）的能力不断增强，但提示设计在很大程度上仍然是启发式的和临时的。本项目将探索“提示最小化”（prompt minimization），即在保持输出保真度的同时，将提示缩减为最小、信息密度最高的形式。实际上，较短的提示可以减少计算开销和推理延迟，尤其是当大型上下文（如整个文档或代码库）被不必要地包含时。此外，较长的提示可能损害LLM的推理能力和准确性。理论上，存在多个产生等效输出的提示，这表明输入空间存在高度冗余，引发了关于哪些信息对于引发特定模型行为至关重要的基本问题。我们提出了三个变体框架来识别和评估最小提示，并证明最小提示通常能产生与其较长版本相当的输出。这些发现为高效的提示工程提供了新方向，并加深了我们对LLM中输入压缩的理解。
英文摘要
Despite the growing capabilities of large language models (LLMs), prompt design remains largely heuristic and ad hoc. This project will explore $\textit{prompt minimization}$, the process of reducing prompts to their smallest, most information-dense form while preserving output fidelity. Practically, shorter prompts reduce computational overhead and inference latency, especially when large contexts, such as entire documents or codebases, are included unnecessarily. Further, longer prompts can damage LLM reasoning and accuracy. Theoretically, the existence of multiple prompts yielding equivalent outputs suggests a high degree of redundancy in the input space, raising fundamental questions about what information is essential to elicit specific model behaviors. We propose three variant frameworks to identify and evaluate minimal prompts and demonstrate that minimal prompts often produce outputs comparable to those of their longer counterparts. These findings suggest new directions for efficient prompt engineering and deepen our understanding of input compression in LLMs.
Comments14 pages, 13 figures
