It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

• URL: http://arxiv.org/abs/2605.20258v1
• Date: Mon, 18 May 2026 13:57:44 GMT
• Title: It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
• Abstract summary: Self-distillation framework that decouples information suppression from task resolution.<n>Self-distillation framework that decouples information suppression from task resolution.
• Score: 73.46918128880786
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 propose SELFCI, a complementary self-distillation framework that decouples information suppression from task resolution. SELFCI jointly optimizes two independent reverse KL divergences over distinct teacher distributions derived from feedback: one encourages preserving task-relevant information for utility, while the other enforces minimal and appropriate disclosure. This complementary formulation induces a Product-of-Experts (PoE) target, aligning the policy with the intersection of capability and privacy requirements. Empirical evaluations demonstrate that SELFCI, without relying on costly external supervision, consistently outperforms competitive baselines such as online reinforcement learning algorithms (e.g., GRPO). These trends further extend to out-of-domain settings involving agentic workflows and accumulated private context, suggesting that SELFCI provides a practical path toward CI alignment.

Related papers

• Demystifying the Privacy-Utility Trade-off in LLM Interactions [17.156111398729863]
  We present a lightweight model Veilmind-4B to drive a dynamic extraction-sanitization-restoration pipeline.<n>Our approach reaches a low-leakage privacy point while preserving substantially higher response utility than existing privacy-oriented baselines.
  arXiv  Detail & Related papers  (2026-09-10T02:12:51Z)
• CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement [50.91045324738942]
  CLAIM is an uncertainty-driven framework for active clarification learning in open-domain settings.<n>We propose an entropy-driven synthetic data generation pipeline that integrates uncertainty estimation with semantic clustering and reasoning-based judgments.<n> Experimental results demonstrate that CLAIM can learn stable and generalizable clarification strategies without relying on manually labeled data.
  arXiv  Detail & Related papers  (2026-08-12T04:27:45Z)
• Reinforcing privacy reasoning in LLMs via normative simulacra from fiction [1.143869785127334]
  Contextual Integrity provides a principled framework, defining privacy as the appropriate flow of information within context-relative norms.<n>We propose extracting normative simulacra from fiction novels and using them to fine-tune LLMs.<n>We evaluate on five CI-aligned benchmarks spanning distinct societal contexts.
  arXiv  Detail & Related papers  (2026-04-21T19:16:22Z)
• Causal Bootstrapped Alignment for Unsupervised Video-Based Visible-Infrared Person Re-Identification [52.784239635604735]
  VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images.<n>Existing approaches rely heavily on fully supervised learning with expensive cross-modality annotations, limiting scalability.<n>We propose a Causal Bootstrapped Alignment framework that explicitly exploits inherent video priors.
  arXiv  Detail & Related papers  (2026-04-17T02:15:59Z)
• Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text [0.42821598129654453]
  We develop an on-premise, LLM-driven substitution pipeline that anonymizes text.<n>We measure privacy, semantic utility, and trainability under privacy.<n>Our method attains state-of-the-art privacy, minimal topical drift, strong factual utility, and low trainability loss.
  arXiv  Detail & Related papers  (2026-03-17T23:46:15Z)
• Contextualized Privacy Defense for LLM Agents [84.30907378390512]
  LLM agents increasingly act on users' personal information, yet existing privacy defenses remain limited in both design and adaptability.<n>We propose Contextualized Defense Instructing (CDI), a new privacy defense paradigm.<n>We show that our CDI consistently achieves a better balance between privacy preservation (94.2%) and helpfulness (80.6%) than baselines.
  arXiv  Detail & Related papers  (2026-03-03T13:35:33Z)
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models [55.30555646945055]
  Text-to-Image (T2I) models are vulnerable to semantic leakage.<n>We introduce DeLeaker, a lightweight approach that mitigates leakage by directly intervening on the model's attention maps.<n>SLIM is the first dataset dedicated to semantic leakage.
  arXiv  Detail & Related papers  (2025-10-16T17:39:21Z)
• Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents [43.303548143175256]
  This study proposes an auditing framework for conversational privacy that quantifies an agent's susceptibility to risks.<n>The proposed Conversational Manipulation for Privacy Leakage (CMPL) framework is designed to stress-test agents that enforce strict privacy directives.
  arXiv  Detail & Related papers  (2025-06-11T20:47:37Z)
• Contextual Integrity in LLMs via Reasoning and Reinforcement Learning [41.795843170879046]
  We develop a reinforcement learning framework that instills in models the reasoning necessary to achieve contextual integrity.<n>We show that our method substantially reduces inappropriate information disclosure while maintaining task performance.
  arXiv  Detail & Related papers  (2025-05-29T21:26:21Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients [54.98496284653234]
  We consider the task of training a policy that maximizes reward while minimizing disclosure of certain sensitive state variables through the actions. We solve this problem by introducing a regularizer based on the mutual information between the sensitive state and the actions. We develop a model-based estimator for optimization of privacy-constrained policies.
  arXiv  Detail & Related papers  (2020-12-30T03:22:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.