This paper surveys research works in the quickly advancing field of instruction tuning (IT), a crucial technique to enhance the capabilities and controllability of large language models (LLMs). Instruction tuning refers to the process of further training LLMs on a dataset consisting of \textsc{(instruction, output)} pairs in a supervised fashion, which bridges the gap between the next-word prediction objective of LLMs and the users' objective of having LLMs adhere to human instructions. In this work, we make a systematic review of the literature, including the general methodology of IT, the construction of IT datasets, the training of IT models, and applications to different modalities, domains and applications, along with an analysis on aspects that influence the outcome of IT (e.g., generation of instruction outputs, size of the instruction dataset, etc). We also review the potential pitfalls of IT along with criticism against it, along with efforts pointing out current deficiencies of existing strategies and suggest some avenues for fruitful research. Project page: github.com/xiaoya-li/Instruction-Tuning-Survey

翻译：本文综述了指令微调（Instruction Tuning, IT）这一快速发展领域的研究工作，该技术是增强大语言模型（Large Language Models, LLMs）能力与可控性的关键技术。指令微调是指基于由（指令，输出）对组成的数据集，以监督方式对大语言模型进行进一步训练的过程，这弥合了大语言模型的下一个词预测目标与用户期望其遵循人类指令之间的差距。本文对相关文献进行了系统性梳理，涵盖指令微调的一般方法论、指令数据集构建、指令模型训练、在不同模态、领域与应用中的实践，并分析了影响指令微调效果的因素（如指令输出生成、指令数据集规模等）。此外，本文还探讨了指令微调的潜在缺陷及其批判性观点，以及针对当前策略不足之处的改进方向，并提出未来富有前景的研究路径。项目主页：github.com/xiaoya-li/Instruction-Tuning-Survey