It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling sensitive workflows, adhering to CI becomes critical. However, even frontier models remain unreliable in making disclosure decisions, and existing mitigation strategies often degrade underlying task performance. To overcome this privacy-utility trade-off, we
Record details
Published: 18 May 2026
Source: arXiv
Category: Research
Topics: Privacy · Agents & autonomy · Transparency
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Governing AI-Assisted Security Operations: A Design Science Framework for Operational Decision Support
arXiv · 10 May 2026
ADAPTS: Agentic Decomposition for Automated Protocol-agnostic Tracking of Symptoms
arXiv · 4 May 2026
TRUST: A Framework for Decentralized AI Service v.0.1
arXiv · 29 April 2026
VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering
arXiv · 11 March 2026
Accountable yet Anonymous AI Agents - Split-Knowledge Binding in National Agent-Identity Layer in China
arXiv cs.CY · 28 July 2026
PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
HuggingFace Daily Papers · 5 August 2026
How to cite this record
ethics.ai (18 May 2026), “It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs,” evidence record 4113, https://ethics.ai/record/4113 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.