Toxicity
السمّية
توليد النموذج لمحتوى مسيء أو ضار أو تمييزي، وهو من المقاييس الرئيسية لسلامة النماذج اللغوية الكبيرة.
Model generation of offensive, harmful, or discriminatory content — one of the key safety metrics for large language models.
Also translated asالتوليد الضار، السمّية اللغوية، الفساد الدلالي للمخرجات، المحتوى السامّ، المحتوى الضار، توليد نصوص هجومية أو بذيئة أو تحريضية
First appears in this corpus in: Scaling Language Models: Methods, Analysis & Insights from Training Gopher (2022)
Appears in these papers
- Scaling Language Models: Methods, Analysis & Insights from Training Gopher2022in the sky ✦
- Scaling Language Models: Methods, Analysis & Insights from Training Gopher2022in the sky ✦
- Training Language Models to Follow Instructions with Human Feedback2022in the sky ✦
- OPT: Open Pre-Trained Transformer Language Models2022in 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 ✦