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.

翻译：本文系统综述了指令微调这一快速发展领域的研究工作，该技术是增强大语言模型能力与可控性的关键方法。指令微调是指以监督方式，使用由（指令，输出）对组成的数据集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词预测目标与用户期望模型遵循人类指令之间的差距。本研究对相关文献进行了系统梳理，涵盖指令微调的通用方法论、数据集构建、模型训练、以及在不同模态、领域与应用场景中的实践，同时分析了影响指令微调效果的因素（如指令输出的生成方式、指令数据集的规模等）。本文还探讨了指令微调的潜在缺陷与相关批评，指出了现有策略的不足，并提出了具有前景的研究方向。