Instruction Tuning for Large Language Models: A Survey
ACM Computing Surveys · 31.05.2026 · 58 (7) · 1-36
DOI: 10.1145/3777411 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 08.01.2026. Verfasst von Shengyu Zhang und 10 weiteren Autor:innen. Die Arbeit wurde bisher 129-mal zitiert (Crossref) und nennt 160 Literaturangaben. Gefördert von: Key R & D Projects of the Ministry of Science and Technology.
Abstract (Originalsprache)
This article 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 (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 application, along with analysis of aspects that influence the outcome of IT (e.g., generation of instruction outputs, size of the instruction dataset). 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.
Förderung
- Key R & D Projects of the Ministry of Science and Technology
Zitieren
APA
Zhang, S., Dong, L., Li, X., Zhang, S., Sun, X., Wang, S., Li, J., Hu, R., Zhang, T., Wang, G., & Wu, F. (2026). Instruction Tuning for Large Language Models: A Survey. ACM Computing Surveys, 58(7), 1-36. https://doi.org/10.1145/3777411
Vancouver
Zhang S, Dong L, Li X, Zhang S, Sun X, Wang S, et al. Instruction Tuning for Large Language Models: A Survey. ACM Computing Surveys. 2026;58(7):1-36. doi:10.1145/3777411
BibTeX
@article{Zhang2026,
author = {Zhang, Shengyu and Dong, Linfeng and Li, Xiaoya and Zhang, Sen and Sun, Xiaofei and Wang, Shuhe and Li, Jiwei and Hu, Runyi and Zhang, Tianwei and Wang, Guoyin and Wu, Fei},
title = {Instruction Tuning for Large Language Models: A Survey},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {7},
pages = {1--36},
doi = {10.1145/3777411}
}
EUVIMED