Skip to yearly menu bar Skip to main content


GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction

Rui Yang · Lin Song · Yanwei Li · Sijie Zhao · Yixiao Ge · Xiu Li · Ying Shan

Great Hall & Hall B1+B2 (level 1) #531
[ ] [ Project Page ]
[ Paper [ Poster [ OpenReview
Wed 13 Dec 3 p.m. PST — 5 p.m. PST


This paper aims to efficiently enable Large Language Models (LLMs) to use multi-modal tools.The advanced proprietary LLMs, such as ChatGPT and GPT-4, have shown great potential for tool usage through sophisticated prompt engineering.Nevertheless, these models typically rely on prohibitive computational costs and publicly inaccessible data.To address these challenges, we propose the GPT4Tools based on self-instruct to enable open-source LLMs, such as LLaMA and OPT, to use tools.It generates an instruction-following dataset by prompting an advanced teacher with various multi-modal contexts.By using the Low-Rank Adaptation (LoRA) optimization, our approach facilitates the open-source LLMs to solve a range of visual problems, including visual comprehension and image generation.Moreover, we provide a benchmark to evaluate the ability of LLMs to use tools, which is performed in both zero-shot and fine-tuning ways.Extensive experiments demonstrate the effectiveness of our method on various language models, which not only significantly improves the accuracy of invoking seen tools, but also enables the zero-shot capacity for unseen tools.

Chat is not available.