MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting

Tatsuro Inaba; Hirokazu Kiyomaru; Fei Cheng; Sadao Kurohashi

ACL 2023short26 citations

MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting

Tatsuro Inaba, Hirokazu Kiyomaru, Fei Cheng, Sadao Kurohashi

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.

BibTeX

@inproceedings{inaba-etal-2023-multitool,
    title = "{M}ulti{T}ool-{C}o{T}: {GPT}-3 Can Use Multiple External Tools with Chain of Thought Prompting",
    author = "Inaba, Tatsuro  and
      Kiyomaru, Hirokazu  and
      Cheng, Fei  and
      Kurohashi, Sadao",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-short.130/",
    doi = "10.18653/v1/2023.acl-short.130",
    pages = "1522--1532"
}