mlsanityData to 14 Oct 2026

Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications

arXiv 2608.23870 ↗First posted 24 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

When it comes to safety policies for generative AI, one size does not fit all. Each organization and use case needs to mitigate different risks depending on the application context, regulatory environment, organizational values, and user personas. Yet, existing policy specification approaches are designed for traditional access control and fail to capture the nuances of GenAI application: the enforcement of content-based constraints. We present two contributions to address this gap: (1) the Actionable Policy schema, a YAML-based format for specifying what model responses can and cannot contain. The schema enables exception-based policy governance, proposing exceptions to track policy violations; (2) synthetic data generation pipeline that produces policy-aligned training data for model alignment and testing, and a set of tools to help define the schema and enforce policy. Together, these enable organizations to specify policies once and enforce them throughout the GenAI application lifecycle: from model alignment to runtime monitoring. The Actionable Policy schema, example policies, and tools are available as open source: https://github.com/ibm-granite/granite.trust.policy-tools We welcome new ideas, contributions and feedback.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 56 references that are in the map. First posted on arXiv 24 Aug 2026.

Builds on

34 of 56 references.

References · 34

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2017Deep reinforcement learning from human preferencescited by 3,912
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  6. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  7. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  8. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  9. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 839
  10. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  11. 2023XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Modelscited by 505
  12. 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attackcited by 390
22 more
  1. 2024Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothingcited by 346
  2. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervisioncited by 318
  3. 2024Rethinking Machine Unlearning for Large Language Modelscited by 257
  4. 2025Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrailscited by 132
  5. 2024The Art of Saying No: Contextual Noncompliance in Language Modelscited by 105
  6. 2024Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Modelscited by 99
  7. 2024AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policiescited by 74
  8. 2024CodecLM: Aligning Language Models with Tailored Synthetic Datacited by 39
  9. 2023Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curationcited by 38
  10. 2024AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policiescited by 37
  11. 2024PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI Systemcited by 31
  12. 2023Unveiling Safety Vulnerabilities of Large Language Modelscited by 27
  13. 2025Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuningcited by 21
  14. 2024MAP: Multi-Human-Value Alignment Palettecited by 20
  15. 2025Activated LoRA: Fine-tuned LLMs for Intrinsicscited by 12
  16. 2024Alignment Studio: Aligning Large Language Models to Particular Contextual Regulationscited by 10
  17. 2025AI Risk Atlas: Taxonomy and Tooling for Navigating AI Risks and Resourcescited by 8
  18. 2025Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgettingcited by 8
  19. 2025Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topicscited by 6
  20. 2024Value Alignment from Unstructured Textcited by 4
  21. 2025The Unified Control Framework: Establishing a Common Foundation for Enterprise AI Governance, Risk Management and Regulatory Compliancecited by 4
  22. 2025Who's Sorry Now: User Preferences Among Rote, Empathic, and Explanatory Apologies from LLM Chatbotscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Alignment to Access Control: A Framework for GenAI Policy Enforcement
  2. 2025Policy-Aware Generative AI for Safe, Auditable Data Access Governance
  3. 2024A Safe Harbor for AI Evaluation and Red Teaming
  4. 2025Rethinking Autonomy: Preventing Failures in AI-Driven Software Engineering
  5. 2025How Generative AI Empowers Attackers and Defenders Across the Trust & Safety Landscape
  6. 2025Executable Governance for AI: Translating Policies into Rules Using LLMs
  7. 2026COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
  8. 2026From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI