Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Zhihan Zhang, Shuohang Wang, Wenhao Yu, Xu Yi‐chong, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang · 2023
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 outof-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. 1 * This work was done when Zhihan was an intern at Microsoft Azure AI.1 Model and code are available at https://github.com/ ytyz1307zzh/Auto-Instruct.2 A scenario where no additional training or validation data are available for hyperparameter tuning and prompt selection, in addition to the few-shot examples (Perez et al., 2021).