Abstract
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.
Cite
CITATION STYLE
Inaba, T. (2023). Research on “MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting.” Journal of Natural Language Processing, 30(3), 1100–1104. https://doi.org/10.5715/jnlp.30.1100
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.