Self-Consistency
الاتّساق الذاتي
إستراتيجية فكّ ترميز تأخذ عينات من مسارات استدلالية متعددة من النموذج اللغوي وتختار الإجابة النهائية الأكثر تكراراً، مما يُحسّن المتانة مقارنة بسلسلة التفكير أحادية المسار.
A decoding strategy that samples multiple reasoning paths from a language model and selects the most frequent final answer, improving robustness over single-path chain-of-thought.
Also translated asالاتساق الداخلي، التصويت بالأغلبية الاستدلالية، التصويت بالأغلبية على سلاسل التفكير، التوافق الذاتي
First appears in this corpus in: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (2022)
Appears in these papers
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models2022in the sky ✦
- Self-Consistency Improves Chain of Thought Reasoning in Language Models2022in 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 ✦
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models2023in the sky ✦