LINEAiGE
AI HISTORY

LoRA: Low-Rank Adaptation of Large Language Models

Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen submitted 'LoRA: Low-Rank Adaptation of Large Language Models' to arXiv on June 17, 2021. The paper proposes freezing pretrained model weights while injecting trainable low-rank decomposition matrices into Transformer layers to reduce the number of trainable parameters needed for downstream adaptation.

June 17, 2021AI HISTORYVERIFIED

Historical classification

This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.

Why it matters

A documented parameter-efficient adaptation milestone for large pretrained language models, introducing the Low-Rank Adaptation method described in the original paper.

People, organizations & technologies

PEOPLE
Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen

TECHNOLOGIES
LoRA, Low-Rank Adaptation, Transformer models, Parameter-efficient fine-tuning

Evidence & verification

STATE
verified

CONFIDENCE
high

LAST VERIFIED
2026-09-11T07:05:46+08:00

The original arXiv record establishes the title, authors, June 17 2021 initial submission date, and the core low-rank adaptation method recorded here. The authors also link the Microsoft LoRA code repository from the paper record. This candidate records only the paper-submission milestone and does not infer a software-release date, institutional geography, ancestry, influence, causality, or relationships.

Sources

SOURCE 1 · PRIMARY · CLAIM-EVIDENCE

LoRA: Low-Rank Adaptation of Large Language Models

arXiv

PUBLISHED
2021-06-17

SOURCE 2 · PRIMARY · CONTEXT

microsoft/LoRA

Microsoft

Trace the chronology

Record identity

LINEAiGE ID
lora-2021