Preference Model
نموذج التفضيلات
نموذج مُدرَّب على بيانات مقارنة ثنائية (أ مقابل ب) للتنبؤ بالاستجابة المُفضَّلة، ويُستخدم كإشارة مكافأة أثناء تدريب التعلُّم المعزز.
A model trained on pairwise comparison data (A vs B) to predict which response is preferred, used as a reward signal during reinforcement learning training.
Also translated asنموذج التفضيل، نموذج المقارنة
First appears in this corpus in: WebGPT: Browser-Assisted Question-Answering with Human Feedback (2021)
Appears in these papers
- Constitutional AI: Harmlessness from AI Feedback2022in the sky ✦
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned2022in the sky ✦
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned2022in the sky ✦
- WebGPT: Browser-Assisted Question-Answering with Human Feedback2021in the sky ✦