Chain-of-Thought Prompting
تلقين سلسلة التفكير
استراتيجية تلقين تطلب من النموذج اللغوي إظهار خطوات الاستدلال الوسيطة قبل تقديم الإجابة النهائية. لا تنفع إلا في النماذج الأكبر حجماً وتُعدّ من القدرات الناشئة.
A prompting strategy that asks the language model to produce intermediate reasoning steps before giving the final answer. Only effective in sufficiently large models and is itself considered an emergent ability.
Also translated asالتلقين بسلسلة الأفكار، الاستدلال المتسلسل
First appears in this corpus in: Emergent Abilities of Large Language Models (2022)
Appears in these papers
- Emergent Abilities of Large Language Models2022in the sky ✦
- Emergent Abilities of Large Language Models2022in the sky ✦
- PaLM: Scaling Language Modeling with Pathways2022in the sky ✦
- Self-Consistency Improves Chain of Thought Reasoning in Language Models2022in the sky ✦
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models2023in the sky ✦
- Voyager: An Open-Ended Embodied Agent with Large Language Models2023in the sky ✦