如何用提示词做事
How To Do Things With Prompts
浏览论文内容
中文总结 AI 辅助
本文通过语料库分析2023至2025年ChatGPT提示词，发现用户指令趋向间接含蓄、礼貌标记减少，命题内容变化最大（14.9个百分点），表明用户视系统为隐含意义解析器，并反思人机语言演变。
中文摘要 AI 辅助
当用户与大型语言模型交流时，他们产生的指令性言语行为，其语用特征既不同于日常对话，也不同于传统的人机交互，并且这些特征会随着用户对系统熟悉程度的提高而发生变化。本文运用言语行为理论和礼貌理论，对从公开共享的ChatGPT对话中提取的2000条英文提示词进行了语料库语用分析，其中1000条来自2023年，1000条来自2025年，数据来源于ShareChat数据集。每条提示词都标注了言外之力、直接性、命题内容以及礼貌标记的存在情况，并比较了这些特征在两个采样年份中的分布。结果显示，指令力的实现方式持续趋向于间接、含蓄和碎片化，同时礼貌标记的使用有所减少。最大的单一变化发生在命题内容上，变化幅度为14.9个百分点，即对请求行动的明确说明让位于对系统推理能力的隐含依赖，这表明用户已经更新了他们对系统能从简化输入中恢复多少信息的模型，将其视为一个能干的隐含意义解析器。我们不应问大型语言模型是否“真正”理解语言，而应问：在我们学会与它们交谈的过程中，我们创造了什么样的语言？
英文摘要
When users address large language models, they produce directive speech acts whose pragmatic features differ from those of both everyday conversation and traditional human-computer interaction, and these features change as users gain familiarity with the systems they address. This paper applies speech act and politeness theory to a corpus-pragmatic analysis of 2,000 English-language prompts drawn from publicly shared ChatGPT conversations, 1,000 from 2023 and 1,000 from 2025, using the ShareChat dataset. Each prompt is annotated for illocutionary force, directness, propositional content, and the presence of politeness markers, and the distribution of these features is compared across the two sampling years. The results show a consistent movement toward indirect, implicit, and fragmentary realizations of directive force, accompanied by a decline in politeness marking. The largest single change, a shift of 14.9 percentage points, occurs in propositional content, where explicit specification of the requested action gives way to implicit reliance on the system's inferential capacity, suggesting that users have updated their model of what the system can recover from reduced input, treating it as a competent implicature resolver. Rather than asking whether LLMs "really" understand language, we should ask: what kind of language have we created in learning to speak to them?
