arXiv cs.CL· Kai Chen, Guisi Ni, Albert Cheu, Kassem Fawaz, Yuzheng Hu, Ryan McKenna, Peter Kairouz·· 2 天前AI 评分22
SHIP：兼顾隐私的结构化分层洞察提取方法
SHIP: Structured and Hierarchical Insight with Privacy
AI 导读
研究者提出 SHIP（Structured and Hierarchical Insight with Privacy），将差分隐私（DP）洞察定义为可复用表示，用于回答分析查询并统一评估其效用。
正文 · 原文
Abstract:Extracting insights from textual data while protecting user privacy is increasingly important. Existing methods produce private insights in diverse forms for different analytical purposes, making their utility difficult to assess and compare. In this work, we formulate differentially private (DP) insights as reusable representations for answering analytical queries, providing a common basis for utility assessment. Answering these queries, however, requires fine-grained details and cross-attribute statistics that existing representations may omit. To capture this information, we introduce Structured and Hierarchical Insight with Privacy (SHIP), which automatically maps queries to attributes, builds a hierarchical hybrid taxonomy, and releases a DP synthetic table for further analysis. We also develop an evaluation protocol based primarily on QA performance and structured fidelity. Our experiments demonstrate SHIP's strong performance on both measures relative to existing private insight baselines, while identifying queries that remain challenging for structured representations.
| Comments: | This paper mainly work on extracting and evaluating insights from textual data |
| Subjects: | Computation and Language (cs.CL); Cryptography and Security (cs.CR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.21048 [cs.CL] |
| (or arXiv:2610.21048v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21048 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kai Chen [view email]
[v1]
Thu, 15 Oct 2026 00:48:25 UTC (264 KB)
来源：arXiv cs.CL · arxiv.org