Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
- URL: http://arxiv.org/abs/2505.14585v1
- Date: Tue, 20 May 2025 16:40:09 GMT
- Title: Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
- Authors: Wenbin Hu, Haoran Li, Huihao Jing, Qi Hu, Ziqian Zeng, Sirui Han, Heli Xu, Tianshu Chu, Peizhao Hu, Yangqiu Song,
- Abstract summary: 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.
- Score: 41.64346961394884
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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 +17.64% 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.
Related papers
- ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning [49.47193675702453]
Large Language Models (LLMs) have demonstrated remarkable generative capabilities.<n>LLMs remain vulnerable to malicious instructions that can bypass safety constraints.<n>We propose a reasoning-based safety alignment framework, ARMOR, that replaces the ad-hoc chains of thought reasoning process with human-aligned, structured one.
arXiv Detail & Related papers (2025-07-14T09:05:54Z) - Towards Trustworthy Federated Learning [26.25193909843069]
This paper develops a comprehensive framework to address three critical trustworthy challenges in federated learning (FL)<n>To improve the system's defense against Byzantine attacks, we develop a Two-sided Norm Based Screening mechanism.<n>We also adopt a differential privacy-based scheme to prevent raw data at local clients from being inferred by curious parties.
arXiv Detail & Related papers (2025-03-05T17:25:20Z) - PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance [44.287734754038254]
We present PrivaCI-Bench, a contextual privacy evaluation benchmark for generative large language models (LLMs)<n>We evaluate the latest LLMs, including the recent reasoner models QwQ-32B and Deepseek R1.<n>Our experimental results suggest that though LLMs can effectively capture key CI parameters inside a given context, they still require further advancements for privacy compliance.
arXiv Detail & Related papers (2025-02-24T10:49:34Z) - The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 [70.94607997570729]
We present a comprehensive safety assessment of OpenAI-o3 and DeepSeek-R1 reasoning models.<n>We investigate their susceptibility to adversarial attacks, such as jailbreaking and prompt injection, to assess their robustness in real-world applications.
arXiv Detail & Related papers (2025-02-18T09:06:07Z) - Assessing confidence in frontier AI safety cases [37.839615078345886]
A safety case presents a structured argument in support of a top-level claim about a safety property of the system.<n>This raises the question of what level of confidence should be associated with a top-level claim.<n>We propose a method by which AI developers can prioritise, and thereby make their investigation of argument defeaters more efficient.
arXiv Detail & Related papers (2025-02-09T06:35:11Z) - OpenAI o1 System Card [274.83891368890977]
The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought.<n>This report outlines the safety work carried out for the OpenAI o1 and OpenAI o1-mini models, including safety evaluations, external red teaming, and Preparedness Framework evaluations.
arXiv Detail & Related papers (2024-12-21T18:04:31Z) - Deliberative Alignment: Reasoning Enables Safer Language Models [64.60765108418062]
We introduce Deliberative Alignment, a new paradigm that teaches the model safety specifications and trains it to explicitly recall and accurately reason over the specifications before answering.<n>We used this approach to align OpenAI's o-series models, and achieved highly precise adherence to OpenAI's safety policies, without requiring human-written chain-of-thoughts or answers.
arXiv Detail & Related papers (2024-12-20T21:00:11Z) - How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review [15.15468770348023]
We evaluate large language models' performance in privacy-related tasks such as privacy information extraction (PIE), legal and regulatory key point detection (KPD), and question answering (QA)<n>Through an empirical assessment, we investigate the capacity of several prominent LLMs, including BERT, GPT-3.5, GPT-4, and custom models, in executing privacy compliance checks and technical privacy reviews.<n>While LLMs show promise in automating privacy reviews and identifying regulatory discrepancies, significant gaps persist in their ability to fully comply with evolving legal standards.
arXiv Detail & Related papers (2024-09-04T01:51:37Z) - ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming [64.86326523181553]
ALERT is a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy.
It aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models.
arXiv Detail & Related papers (2024-04-06T15:01:47Z)
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.