@techreport{peng2023instruction,
author = {Peng, Baolin and Li, Chunyuan and He, Pengcheng and Galley, Michel and Gao, Jianfeng},
title = {Instruction Tuning with GPT-4},
institution = {Microsoft},
year = {2023},
month = {April},
abstract = {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.},
url = {http://approjects.co.za/?big=en-us/research/publication/instruction-tuning-with-gpt-4/},
number = {MSR-TR-2023-35},
note = {Project Page: https://instruction-tuning-with-gpt-4.github.io/},
}