BriefGPT.xyz
Nov, 2023
通过思维树增强跨语言多步推理
Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
HTML
PDF
Leonardo Ranaldi, Fabio Massimo Zanzotto
TL;DR
本研究通过一种自洽的跨语言提示机制，提出了一种跨语言多步推理方法，可以在不同语言中实现多步推理路径，从而达到解决复杂推理任务的目的，并在实验评估中表现出比现有提示方法更优的性能。
Abstract
Chain-of-Thought (CoT) prompting empowers the
reasoning abilities
of Large Language Models (LLMs), eliciting them to solve complex reasoning tasks step-by-step. However, with the success of CoT methods, the ability to deliver
→