Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning. Unfortunately, the performance of LLMs is greatly influenced by the quality of these instructions, and manually writing effective instructions for each task is a laborious and subjective process. In this paper, we introduce Auto-Instruct, a novel method to automatically improve the quality of instructions provided to LLMs. Our method leverages the inherent generative ability of LLMs to produce diverse candidate instructions for a given task, and then ranks them using a scoring model trained on a variety of 575 existing NLP tasks. In experiments on 118 out-of-domain tasks, Auto-Instruct surpasses both human-written instructions and existing baselines of LLM-generated instructions. Furthermore, our method exhibits notable generalizability even with other LLMs that are not incorporated into its training process.
@article{arxiv.2310.13127,
title = {Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models},
author = {Zhihan Zhang and Shuohang Wang and Wenhao Yu and Yichong Xu and Dan Iter and Qingkai Zeng and Yang Liu and Chenguang Zhu and Meng Jiang},
journal= {arXiv preprint arXiv:2310.13127},
year = {2023}
}
Comments
Accepted to EMNLP 2023 Findings. Work was done before July 2023