Evaluating feature steering: A case study in mitigating social biases - Anthropic

Retrieved on: 2024-10-25 18:58:11

Tags for this article:

Click the tags to see associated articles and topics

Evaluating feature steering: A case study in mitigating social biases - Anthropic. View article details on hiswai:

Excerpt

A new piece of Anthropic research by Durmus et al.: "Evaluating feature steering: A case study in mitigating social biases"

Article found on: www.anthropic.com