Improving Model Safety Behavior with Rule-Based Rewards
2024-07-24
·
via OpenAI News
We've developed and applied a new method leveraging Rule-Based Rewards (RBRs) that aligns models to behave safely withou
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
