Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model

Cheng Qian, Chenyan Xiong, Zhenghao Liu, Zhiyuan Liu

Abstract
Large Language Models (LLMs) have demonstrated remarkable progress in utilizing tools, but their closed-source nature and high inference costs pose limitations on their adaptability, necessitating a valid method that leverages smaller, open-sourced models. In this paper, we introduce Toolink, a comprehensive framework that performs task-solving by first creating a toolkit and then integrating the planning and calling of tools through a chain-of-solving (CoS) approach. We first validate the efficacy of Toolink in harnessing the model’s creativity and CoS ability on ChatGPT. Subsequently, we curate CoS-GPT, a chain-of-solving dataset designed for tool-using, and finetune the LLaMA-7B model. It results in LLaMA-CoS, a powerful open-source model with advanced tool-planning and tool-calling capabilities. Evaluation of diverse tasks from BIG-bench demonstrates its CoS ability matches that of ChatGPT while its performance surpasses the chain-of-thought approach. Further studies highlight the generalization of LLaMA-CoS to unseen tasks and showcase its capability in using toolkits not explicitly tailored for the target task, affirming its robustness in real-world scenarios. All codes and data are released.
Anthology ID:
2024.naacl-long.48
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
831–854
Language:
URL:
https://aclanthology.org/2024.naacl-long.48
DOI:
10.18653/v1/2024.naacl-long.48
Bibkey:
Cite (ACL):
Cheng Qian, Chenyan Xiong, Zhenghao Liu, and Zhiyuan Liu. 2024. Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 831–854, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model (Qian et al., NAACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2024.naacl-long.48.pdf
PDF Search