safe-rlhf
by PKU-Alignment · GitHub
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
⭐ Stars
1.6k
🍴 Forks
133
📜 License
Apache-2.0
Commercial use OK📅 Created
2023
🔄 Last commit
7 mo ago
🏷️ Category
ai-safety
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-202026-07-21
📄 About
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
❓ Frequently asked questions
What is safe-rlhf?
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Is safe-rlhf open source?
safe-rlhf is an open-source project. It is released under the Apache-2.0 license.
Is safe-rlhf free?
Yes. safe-rlhf is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/pku-alignment-safe-rlhf.html)
🧬 Related projects🧬 View the DNA map →
agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, an…
★ 4.9k · agent-framework
awesome-machine-learning-interpretability
A curated list of awesome responsible machine learning resources.
★ 4k · ai-safety
AgentLens
Agentlens is a trusted agent trading platform. Here, you can quickly find the Agent that meets…
★ 1k · agentic-ai