Human Feedback
التغذية الراجعة البشرية
أحكام تفضيل أو عروض توضيحية يقدّمها مقيّمون بشريون لتوجيه تدريب النموذج نحو السلوك المرغوب.
Preference judgments or demonstrations provided by human labelers to guide model training toward desired behavior.
Also translated asالتقييم البشري، الملاحظات البشرية، تغذية راجعة بشرية
First appears in this corpus in: Deep Reinforcement Learning from Human Preferences (2017)
Appears in these papers
- Deep Reinforcement Learning from Human Preferences2017in the sky ✦
- Deep Reinforcement Learning from Human Preferences2017in the sky ✦
- Training Language Models to Follow Instructions with Human Feedback2022in the sky ✦
- Training Language Models to Follow Instructions with Human Feedback2022in the sky ✦
- Learning to Summarize from Human Feedback2020in the sky ✦
- Learning to Summarize from Human Feedback2020in the sky ✦
- LIMA: Less Is More for Alignment2023in the sky ✦
- WebGPT: Browser-Assisted Question-Answering with Human Feedback2021in the sky ✦