MultiTool-CoT:GPT-3 可通过思维链提示使用多个外部工具
MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting
AI总结:
本文提出 MultiTool-CoT 框架,通过思维链提示让 GPT-3 在推理中调用计算器和知识检索器等多个外部工具,在 NumGLUE Task 2 上取得最先进性能。
摘要:
大型语言模型(LLMs)在各种推理任务上已取得令人瞩目的性能。为进一步提升性能,我们提出 MultiTool-CoT,这是一个新颖的框架,利用思维链(CoT)提示在推理过程中整合多个外部工具,例如计算器和知识检索器。我们将 MultiTool-CoT 应用于 NumGLUE 的 Task 2 数据集,该任务同时需要数值推理和领域特定知识。实验表明,我们的方法显著优于强基线,并取得了最先进的性能。
英文摘要:
Large language models (LLMs) have achieved impressive performance on various reasoning tasks. To further improve the performance, we propose MultiTool-CoT, a novel framework that leverages chain-of-thought (CoT) prompting to incorporate multiple external tools, such as a calculator and a knowledge retriever, during the reasoning process. We apply MultiTool-CoT to the Task 2 dataset of NumGLUE, which requires both numerical reasoning and domain-specific knowledge. The experiments show that our method significantly outperforms strong baselines and achieves state-of-the-art performance.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。