# Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.14585 · HTML: https://mlsanity.com/paper/2505.14585/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 36 of its 43 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://mlsanity.com/paper/2304.05197/) (2023)
- [Certified Defenses for Data Poisoning Attacks](https://mlsanity.com/paper/1706.03691/) (2017)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory](https://mlsanity.com/paper/2310.17884/) (2023)
- [How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy](https://mlsanity.com/paper/2303.00654/) (2023)
- [Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast](https://mlsanity.com/paper/2402.08567/) (2024)
- [Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks](https://mlsanity.com/paper/2006.12557/) (2020)
- [Efficient Adversarial Training in LLMs with Continuous Attacks](https://mlsanity.com/paper/2405.15589/) (2024)
- [Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism](https://mlsanity.com/paper/2305.18438/) (2023)
- [Can Indirect Prompt Injection Attacks Be Detected and Removed?](https://mlsanity.com/paper/2502.16580/) (2025)
- [Privately Fine-Tuning Large Language Models with Differential Privacy](https://mlsanity.com/paper/2210.15042/) (2022)

## Built on by (most cited first, 8 of 8)

- [A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models](https://mlsanity.com/paper/2509.03871/) (2025)
- [Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance](https://mlsanity.com/paper/2509.22250/) (2025)
- [Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations](https://mlsanity.com/paper/2604.00209/) (2026)
- [It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs](https://mlsanity.com/paper/2605.20258/) (2026)
- [HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong](https://mlsanity.com/paper/2507.11502/) (2025)
- [Reinforcing privacy reasoning in LLMs via normative simulacra from fiction](https://mlsanity.com/paper/2604.20904/) (2026)
- [Adversarial Reframing: A Framework for Targeted Generation in Language Models](https://mlsanity.com/paper/2605.21674/) (2026)
- [MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models](https://mlsanity.com/paper/2609.39107/) (2026)

## Abstract (arXiv)

While Large Language Models (LLMs) exhibit remarkable capabilities, they also introduce significant safety and privacy risks. Current mitigation strategies often fail to preserve contextual reasoning capabilities in risky scenarios. Instead, they rely heavily on sensitive pattern matching to protect LLMs, which limits the scope. Furthermore, they overlook established safety and privacy standards, leading to systemic risks for legal compliance. To address these gaps, we formulate safety and privacy issues into contextualized compliance problems following the Contextual Integrity (CI) theory. Under the CI framework, we align our model with three critical regulatory standards: GDPR, EU AI Act, and HIPAA. Specifically, we employ reinforcement learning (RL) with a rule-based reward to incentivize contextual reasoning capabilities while enhancing compliance with safety and privacy norms. Through extensive experiments, we demonstrate that our method not only significantly enhances legal compliance (achieving a +8.58% accuracy improvement in safety/privacy benchmarks) but also further improves general reasoning capability. For OpenThinker-7B, a strong reasoning model that significantly outperforms its base model Qwen2.5-7B-Instruct across diverse subjects, our method enhances its general reasoning capabilities, with +2.05% and +8.98% accuracy improvement on the MMLU and LegalBench benchmark, respectively.