仅通过API调用大模型生成私有表格数据，效果不如传统方法。
Is API Access to LLMs Useful for Generating Private Synthetic Tabular Data?
- 基于查询工作负载设计距离度量，适配表格数据的私密生成
- 仅需一次API调用，无需持续交互，提升效率与隐私保护
- 发现大模型API访问未必提升生成质量，提出优化方向
差分隐私（DP）合成数据是实现敏感数据分析的有力工具。近年来，大语言模型（LLMs）的发展推动了多项改进DP合成数据生成的技术。一类方法依赖于对基础模型权重进行差分隐私微调，但顶尖模型的权重可能不公开。本文提出两种仅需基础模型API访问即可生成差分隐私表格数据的新算法。我们拓展了专为图像和文本设计的Private Evolution算法（Lin et al., 2023; Xie et al., 2024），引入基于查询工作负载的距离度量，该度量本身具有独立价值。我们还提出一族使用一次性API调用而非自适应查询的算法。研究发现，仅通过API访问强大大模型，并未在所有情况下提升DP合成数据的质量，相比无需此类访问的现有基线方法表现更差。我们深入分析其原因，并提出可使大模型更适用于该任务的改进方向。
原文摘要 · Abstract (English)
Differentially private (DP) synthetic data is a versatile tool for enabling the analysis of private data. Recent advancements in large language models (LLMs) have inspired a number of algorithm techniques for improving DP synthetic data generation. One family of approaches uses DP finetuning on the foundation model weights; however, the model weights for state-of-the-art models may not be public. In this work we propose two DP synthetic tabular data algorithms that only require API access to the foundation model. We adapt the Private Evolution algorithm (Lin et al., 2023; Xie et al., 2024) -- which was designed for image and text data -- to the tabular data domain. In our extension of Private Evolution, we define a query workload-based distance measure, which may be of independent interest. We propose a family of algorithms that use one-shot API access to LLMs, rather than adaptive queries to the LLM. Our findings reveal that API-access to powerful LLMs does not always improve the quality of DP synthetic data compared to established baselines that operate without such access. We provide insights into the underlying reasons and propose improvements to LLMs that could make them more effective for this application.
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。