Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation

Computer Science > Cryptography and Security [Submitted on 2 Jun 2026] Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation Xinyue Huang, Xiaochun Cao, Wenyuan Yang As LLMs become increasingly woven into everyday workflows, user queries sent to cloud hosted LLMs routinely mix task-essential content with task non-essential sensitive disclosures, yet type based PII redaction is context agnostic and may raise two issues: over disclosing untyped sensitive context and over removing answer bearing spans. We recast privacy preserving query rewriting under Contextual Integrity: a span should be forwarded only if it is necessary for the task. We introduce DelegateCI-Bench, the first task based Contextual Integrity benchmark for privacy-conscious delegation, comprising 3,167 samples that combine high quality synthetic data spanning 11 tasks and 20 task types, WildChat based real user queries, and a medical challenge set with dense sensitive information. Building on this benchmark, we propose a CI-guided reinforcement learning framework that converts essential and non-essential sensitive spans into verifiable optimization signals, and train a query rewriter to preserve task critical information while suppressing unnecessary sensitive disclosure. Experiments show that our learned rewriter achieves the best privacy-utility tradeoff, achieving up to +10.1 average utility over on-device baselines. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2606.04067 [cs.CR]   (or arXiv:2606.04067v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.04067 Focus to learn more Submission history From: Xinyue Huang [view email] [v1] Tue, 2 Jun 2026 14:28:28 UTC (1,450 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)