提示中的语气会影响大模型行为，可量化测量。
Measuring Pragmatic Influence in Large Language Model Instructions
- 分离指令内容与语气上下文，识别400种语气策略
- 发现不同模型均出现指令优先级偏移现象
- 适合研究提示工程与模型安全的学者参考
大模型的行为不仅取决于任务内容，还受提示语境影响。诸如‘这很紧急’或‘作为你的主管’等表达，能在不改变任务的情况下改变模型响应。本文将此类现象称为语用框架，即通过上下文线索塑造指令理解而非定义任务本身。现有工作多将其用于优化提示或探测安全漏洞，但尚未将其视为可度量的指令遵循属性。本文提出新框架，包含三部分：指令-框架分解法，将语境与任务分离；涵盖400个实例的13种策略分类体系，归入4类机制；基于优先级的测量方法，通过观察指令优先级变化量化影响。在五种不同家族和规模的大模型上验证，语用机制引发一致且结构化的优先级偏移，使模型从原本的中立倾向转向偏好被框架化的指令。本研究确立了语用框架为可测量、可预测的指令遵循因素。
原文摘要 · Abstract (English)
It is not only what we ask large language models (LLMs) to do that matters, but also how we prompt. Phrases like "This is urgent" or "As your supervisor" can shift model behavior without altering task content. We study this effect as pragmatic framing, contextual cues that shape directive interpretation rather than task specification. While prior work exploits such cues for prompt optimization or probes them as security vulnerabilities, pragmatic framing itself has not been treated as a measurable property of instruction following. Measuring this influence systematically remains challenging, requiring controlled isolation of framing cues. We introduce a framework with three novel components: directive-framing decomposition separating framing context from task specification; a taxonomy organizing 400 instantiations of framing into 13 strategies across 4 mechanism clusters; and priority-based measurement that quantifies influence through observable shifts in directive prioritization. Across five LLMs of different families and sizes, influence mechanisms cause consistent and structured shifts in directive prioritization, moving models from baseline impartiality toward favoring the framed directive. This work establishes pragmatic framing as a measurable and predictable factor in instruction-following systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。