{
 "title": "零樣本與少樣本學習（Zero-shot / Few-shot Learning）是什麼？",
 "site": "AI 與科技名詞白話解釋",
 "canonical": "https://glossary.penguindriver.com/t/few-shot",
 "markdown": "https://glossary.penguindriver.com/t/few-shot.md",
 "summary": "零樣本與少樣本學習是指大型語言模型在不更新參數的情況下，僅憑提示詞中的說明或少量範例完成新任務，也稱為情境學習。OpenAI 2020 年發表 GPT-3 論文〈Language Models are Few-Shot Learners〉，展示 1,750 億參數模型在多種任務上用少樣本方式就有接近微調模型的表現。",
 "date_modified": "2026-09-28",
 "retrieved": "2026-09-29",
 "content_sha256": "33296b4770d5543288be097223019bf3dfbd17cea262f465ab7113c5ecc8e43a",
 "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%2Ffew-shot&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"
  }
 ],
 "source_count": 1,
 "cite_as": {
  "zh": "零樣本與少樣本學習（Zero-shot / Few-shot Learning）是什麼？｜AI 與科技名詞白話解釋。https://glossary.penguindriver.com/t/few-shot（資料日期 2026-09-28，擷取 2026-09-29）",
  "apa": "AI 與科技名詞白話解釋. (2026). 零樣本與少樣本學習（Zero-shot / Few-shot Learning）是什麼？. Retrieved 2026-09-29, from https://glossary.penguindriver.com/t/few-shot",
  "markdown": "[零樣本與少樣本學習（Zero-shot / Few-shot Learning）是什麼？](https://glossary.penguindriver.com/t/few-shot)（AI 與科技名詞白話解釋，2026-09-28）"
 },
 "license": "可引用，請附上正式網址與資料日期"
}