Chain of Thought
سلسلة التفكير
سلسلة من خطوات الاستدلال الوسيطة بلغة طبيعية تسبق الإجابة النهائية، تُضاف إلى أمثلة التحفيز لتمكين النموذج اللغوي من محاكاة التفكير المرحلي دون تدريب إضافي.
A series of intermediate natural-language reasoning steps preceding the final answer, added to few-shot exemplars so that a language model imitates step-by-step thinking without additional training.
Also translated asأثر التفكير، الاستدلال المتسلسل، الاستدلال المتسلسل الخطوات، الاستدلال خطوة بخطوة، التحفيز بسلسلة الأفكار، التفكير التسلسلي، التفكير المتسلسل، التفكير المنطقي التتابعي، سلسلة الاستدلال
First appears in this corpus in: A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence (1956)
Appears in these papers
- Mastering the Game of Go with Deep Neural Networks and Tree Search2016in the sky ✦
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models2022in the sky ✦
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models2022in the sky ✦
- Constitutional AI: Harmlessness from AI Feedback2022in the sky ✦
- A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence1956in the sky ✦
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning2025in the sky ✦
- DeepSeek-V3 Technical Report2024in the sky ✦
- Gemini: A Family of Highly Capable Multimodal Models2023in the sky ✦
- Generative Agents: Interactive Simulacra of Human Behavior2023in the sky ✦
- Scaling Language Models: Methods, Analysis & Insights from Training Gopher2022in the sky ✦
- GPT-4 Technical Report2023in the sky ✦
- Visual Instruction Tuning2023in the sky ✦
- Learning to Reason with LLMs2024in the sky ✦
- Learning to Reason with LLMs2024in the sky ✦
- ReAct: Synergizing Reasoning and Acting in Language Models2023in the sky ✦
- RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback2023in the sky ✦
- RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback2023in the sky ✦
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control2023in the sky ✦
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances2022in the sky ✦
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances2022in the sky ✦
- Self-Consistency Improves Chain of Thought Reasoning in Language Models2022in the sky ✦
- Sparks of Artificial General Intelligence: Early Experiments with GPT-42023in the sky ✦
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models2023in the sky ✦
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models2023in the sky ✦
- WebArena: A Realistic Web Environment for Building Autonomous Agents2023in the sky ✦
- WebArena: A Realistic Web Environment for Building Autonomous Agents2023in the sky ✦