Menu

View

JournalDigital

Theme

LightDarkSystem

Text size

AAA

The paper in your inbox every morning

Straight from the source · Glossary

The Tech Gazette

RLHF

Reinforcement learning from human feedback: tuning a model with people's ratings of its answers so it becomes more helpful and follows instructions.

Read more at en.wikipedia.org →

In the news

1. arXiv cs.MAOct 14, 2026Research
   From Training to Escalation: Forensic Analysis and Local Recreation of RL/RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)
2. arXiv cs.HCOct 7, 2026Research
   A Scoping Review and Experimental Study on Reinforcement Learning from Human Feedback for Human-Robot Collaboration
3. arXiv cs.AISep 28, 2026Research
   Using Context Is Not Enough: Test-Time Training for Personalized Reward Modeling