用小模型预判隐私保护后提示词效果，避免大模型资源浪费。
Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions
- 用小模型预测经差分隐私处理的提示词在大模型上的表现。
- 实验显示可避免20%提示词的无效计算资源消耗。
- 揭示经典论文中隐含的性能影响选择，提醒谨慎设计。
在线大语言模型交互引发隐私问题，服务方可能从用户提示中获取敏感信息。尽管可通过差分隐私对文本提示进行净化，但我们发现难以提前预估净化后提示在大模型上的表现。性能不佳会带来显著经济损失（按使用量计费的服务）及大量计算资源浪费。为此，我们提出一种中间件架构，利用小语言模型在发送至大模型前预测给定净化提示的效用。我们在摘要和翻译任务上进行实验，结果表明该架构可防止高达20%的提示产生无效计算。研究过程中，我们复现了一篇引用极高的文本净化论文实验，发现一个潜在的性能驱动实现选择会显著改变输出，但原论文未明确说明。
原文摘要 · Abstract (English)
Interactions with online Large Language Models raise privacy issues where providers can gather sensitive information about users and their companies from the prompts. While textual prompts can be sanitized using Differential Privacy, we show that it is difficult to anticipate the performance of an LLM on such sanitized prompt. Poor performance has clear monetary consequences for LLM services charging on a pay-per-use model as well as great amount of computing resources wasted. To this end, we propose a middleware architecture leveraging a Small Language Model to predict the utility of a given sanitized prompt before it is sent to the LLM. We experimented on a summarization task and a translation task to show that our architecture helps prevent such resource waste for up to 20% of the prompts. During our study, we also reproduced experiments from one of the most cited paper on text sanitization using DP and show that a potential performance-driven implementation choice dramatically changes the output while not being explicitly acknowledged in the paper.
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。