{"ID":3052999,"CreatedAt":"2026-06-04T04:41:36.695875263Z","UpdatedAt":"2026-06-05T11:43:53.432517148Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04067","arxiv_id":"2606.04067","title":"Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation","abstract":"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.","short_abstract":"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 ans...","url_abs":"https://arxiv.org/abs/2606.04067","url_pdf":"https://arxiv.org/pdf/2606.04067v1","authors":"[\"Xinyue Huang\",\"Xiaochun Cao\",\"Wenyuan Yang\"]","published":"2026-06-02T14:28:28Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}