Improving Model Safety Behavior with Rule-Based Rewards

Company news OpenAI Source language: English

We’ve developed and applied a new method leveraging Rule-Based Rewards (RBRs) that aligns models to behave safely without extensive human data collection.

Excerpt

We’ve developed and applied a new method leveraging Rule-Based Rewards (RBRs) that aligns models to behave safely without extensive human data collection.

Short excerpt from the source — open the original for the full text.

Sources

← Back to the daily brief