{
  "@context": "https://schema.org",
  "@type": "TechArticle",
  "@id": "https://anchorfact.org/kb/kb-2026-00062",
  "headline": "LoRA (Low-Rank Adaptation)",
  "description": "LoRA (Low-Rank Adaptation) is a parameter-efficient fine-tuning method for large language models, introduced by Hu et al. from Microsoft in 2021 (arXiv:2106.09685, 19,123 citations as of May 2026). Instead of updating all model parameters during fine-tuning, LoRA injects small, trainable low-rank matrices into the model's weight layers, reducing trainable parameters by up to 10,000x while maintaining near full-fine-tuning performance. The method has become the dominant fine-tuning approach in the open-source LLM community, with 13,547 GitHub stars.",
  "dateCreated": "2026-05-22T14:59:47.498Z",
  "dateModified": "2026-05-22T14:59:47.498Z",
  "author": {
    "@type": "Organization",
    "name": "AnchorFact"
  },
  "publisher": {
    "@type": "Organization",
    "name": "AnchorFact",
    "url": "https://anchorfact.org"
  },
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "anchorfact:confidence": "high",
  "anchorfact:generationMethod": "human_only",
  "citation": []
}