RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation
cs.SE, cs.CR, cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/Aizhouym/raise
Terminology
Sources
- Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Reinforcement Learning via Self-Distillation
- ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
- Debunk the Myth of SFT Generalization
- RLTF: Reinforcement Learning from Unit Test Feedback
- Understanding R1-Zero-Like Training: A Critical Perspective
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Neurosymbolic Characterization for Reliable Access Control Policy Analysis
- AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis
- RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
- Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties