Prior work has shown that finetuning large language models (LLMs) using machine-generated instruction-following data enables such models to achieve remarkable zero-shot capabilities on new tasks, and no human-written instructions are needed. In this paper, we present the first attempt to use GPT-4 to generate instruction-following data for LLM finetuning. Our early experiments on instruction-tuned LLaMA models show that the 52K English and Chinese instruction-following data generated by GPT-4 leads to superior zero-shot performance on new tasks to the instruction-following data generated by previous state-of-the-art models. We also collect feedback and comparison data from GPT-4 to enable a comprehensive evaluation and reward model training. We make our data generated using GPT-4 as well as our codebase publicly available.
@article{arxiv.2304.03277,
title = {Instruction Tuning with GPT-4},
author = {Baolin Peng and Chunyuan Li and Pengcheng He and Michel Galley and Jianfeng Gao},
journal= {arXiv preprint arXiv:2304.03277},
year = {2023}
}
Comments
8 pages. Work in progress. Project page: https://instruction-tuning-with-gpt-4.github.io