Ой тізбегі Подсказка
method
ID: chainofthoughtprompting
Related Papers
LAMBADA: Backward Chaining for Automated Reasoning in Natural Language
AbstractRemarkable progress has been made on automated reasoning with natural text, by using Large Language Models (LLMs) and methods such as Chain-of-Thought prompting and Selection-Inference. These techniques search for proofs …...
ThinkSum: Probabilistic reasoning over sets using large language models
AbstractLarge language models (LLMs) have a substantial capacity for high-level analogical reasoning: reproducing patterns in linear text that occur in their training data (zero-shot evaluation) or in the provided context …...