Reinforcing privacy reasoning in LLMs via normative simulacra from fiction

• URL: http://arxiv.org/abs/2604.20904v1
• Date: Tue, 21 Apr 2026 19:16:22 GMT
• Title: Reinforcing privacy reasoning in LLMs via normative simulacra from fiction
• Abstract summary: 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.
• Score: 1.143869785127334
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Information handling practices of LLM agents are broadly misaligned with the contextual privacy expectations of their users. Contextual Integrity (CI) provides a principled framework, defining privacy as the appropriate flow of information within context-relative norms. However, existing approaches either double inference cost via supervisor-assistant architectures, or fine-tune on narrow task-specific data. We propose extracting normative simulacra (structured representations of norms and information flows) from fiction novels and using them to fine-tune LLMs via supervised learning followed by GRPO reinforcement learning. Our composite reward function combines programmatic signals, including task clarity (subsuming schema validity, construct discrimination, and extraction confidence), structural completeness, internal consistency, and context identification, with an LLM judge that evaluates whether the model's privacy reasoning is grounded in the held-out normative universe of the source text. To mitigate overfitting, we introduce per-completion contrastive scoring: each completion is evaluated against both the correct normative universe and a randomly selected wrong one, teaching the model to condition on context rather than memorize source-specific norms. We evaluate on five CI-aligned benchmarks spanning distinct societal contexts and ablate the contributions of RL and normative grounding. Across seven models, SFT introduces a conservative prior toward restricting information flow, improving recognition of privacy-relevant situations but not the correctness of privacy judgments. GRPO with normative grounding achieves the highest score on a law compliance benchmark and strongest correlation with crowdsourced human privacy expectations, demonstrating that fiction-derived normative simulacra can teach contextual privacy reasoning that transfers to real-world domains.

Related papers

• 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)
• It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs [73.46918128880786]
  Self-distillation framework that decouples information suppression from task resolution.<n>Self-distillation framework that decouples information suppression from task resolution.
  arXiv  Detail & Related papers  (2026-05-18T13:57:44Z)
• ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance [49.524070843587594]
  We propose ContextLens, a semi-rule-based framework that leverages large language models (LLMs) to ground input context in the legal domain.<n>We conduct experiments on existing compliance benchmarks that cover the General Data Protection Regulation () and the EU AI Act.<n>The results suggest that our ContextLens can significantly improve LLMs' compliance assessment and surpass existing baselines without any training.
  arXiv  Detail & Related papers  (2026-04-14T05:35:38Z)
• Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations [26.42147314861997]
  We study contextual privacy as a structured latent representation in large language models (LLMs)<n>We find that the three norm-determining CI parameters are encoded as linearly separable and functionally independent directions in activation space.<n>Despite this internal structure, models still leak private information in practice, revealing a clear gap between concept representation and model behavior.
  arXiv  Detail & Related papers  (2026-03-31T20:23:41Z)
• 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)
• Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning [53.92712851223158]
  We formulate safety and privacy issues into contextualized compliance problems following the Contextual Integrity (CI) theory.<n>Under the CI framework, we align our model with three critical regulatory standards: EU AI Act, and HIPAA.<n>We employ reinforcement learning (RL) with a rule-based reward to incentivize contextual reasoning capabilities while enhancing compliance with safety and privacy norms.
  arXiv  Detail & Related papers  (2025-05-20T16:40:09Z)
• PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action [54.11479432110771]
  PrivacyLens is a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories.<n>We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds.<n>State-of-the-art LMs, like GPT-4 and Llama-3-70B, leak sensitive information in 25.68% and 38.69% of cases, even when prompted with privacy-enhancing instructions.
  arXiv  Detail & Related papers  (2024-08-29T17:58:38Z)
• 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.