Awesome Reinforcement Learning
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Joe Benton — most-cited papers & profile · Reinforcement Learning
← authors
·
overview
Joe Benton
2
papers ·
139
citations ·
6
h-index
University of Oxford
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Constitutional Classifiers: Defending Against Universal Jailbreaks Across Thousands Of Hours Of Red Teaming
2025 · 133 citations
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
2025 · 6 citations
Topics
Prompting
Safety & Alignment
Training Techniques
Evaluation
Efficiency