{
 "title": "大型語言模型（Large Language Model (LLM)）是什麼？",
 "site": "AI 與科技名詞白話解釋",
 "canonical": "https://glossary.penguindriver.com/t/llm",
 "markdown": "https://glossary.penguindriver.com/t/llm.md",
 "summary": "大型語言模型（LLM）是用海量文字訓練、透過預測下一個詞元來理解與產生文字的大型神經網路。2020 年 OpenAI 發表的 GPT-3 有 1,750 億個參數，展示了只給幾個範例就能完成新任務的能力。目前主流 LLM 多採用 Transformer 架構。",
 "date_modified": "2026-09-26",
 "retrieved": "2026-09-28",
 "content_sha256": "69ad081057d3640a399cab33b3045b92dc135b68ada9fac65b857e47a9bdd8f7",
 "fingerprint_basis": "Markdown 版全文，移除贊助行與開頭 front matter，去除頭尾空白",
 "verify": {
  "text_snapshot": "https://glossary.penguindriver.com/cite?path=%2Ft%2Fllm&format=text",
  "how": "下載 text_snapshot 後計算 SHA-256，應與 content_sha256 相同；內容更新時指紋會改變"
 },
 "sources": [
  {
   "name": "Brown et al., Language Models are Few-Shot Learners（GPT-3，arXiv 2005.14165）",
   "url": "https://arxiv.org/abs/2005.14165"
  },
  {
   "name": "Ouyang et al., Training language models to follow instructions with human feedback（arXiv 2203.02155）",
   "url": "https://arxiv.org/abs/2203.02155"
  }
 ],
 "source_count": 2,
 "cite_as": {
  "zh": "大型語言模型（Large Language Model (LLM)）是什麼？｜AI 與科技名詞白話解釋。https://glossary.penguindriver.com/t/llm（資料日期 2026-09-26，擷取 2026-09-28）",
  "apa": "AI 與科技名詞白話解釋. (2026). 大型語言模型（Large Language Model (LLM)）是什麼？. Retrieved 2026-09-28, from https://glossary.penguindriver.com/t/llm",
  "markdown": "[大型語言模型（Large Language Model (LLM)）是什麼？](https://glossary.penguindriver.com/t/llm)（AI 與科技名詞白話解釋，2026-09-26）"
 },
 "license": "可引用，請附上正式網址與資料日期"
}