Back to Search
Start Over
Instruction Tuning with GPT-4
- Publication Year :
- 2023
-
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.<br />Comment: 8 pages. Work in progress. Project page: https://instruction-tuning-with-gpt-4.github.io
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2304.03277
- Document Type :
- Working Paper