Content Moderation

إشراف المحتوى

عملية مراجعة المحتوى الرقمي وتصفيته لضمان التزامه بسياسات المنصة ومعايير الأمان. في سياق النماذج اللغوية، تشمل كشف المخرجات الضارة وتصنيفها ومنعها.

The process of reviewing and filtering digital content to ensure compliance with platform policies and safety standards. In the context of language models, includes detecting, classifying, and preventing harmful outputs.

Also translated asمراقبة المحتوى، تعديل المحتوى

First appears in this corpus in: Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned (2022)

Appears in these papers

Mistral 7B2023 in the sky ✦
Mistral 7B2023 in the sky ✦
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned2022 in the sky ✦
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned2022 in the sky ✦