{
  "id": "few-shot-prompting",
  "code": "PTL-0009",
  "term": "Few-shot Prompting",
  "aliases": [
    "k-shot prompting",
    "in-context examples"
  ],
  "category": "foundations",
  "definition": "Few-shot prompting includes a small number of input-output examples in the prompt so the model can infer the task and the desired format from demonstrations.",
  "description": "Popularized by the GPT-3 paper, it allows a model to perform new tasks without any weight updates. Results are sensitive to which examples are chosen, their order, and their label balance, which spawned a body of work on exemplar selection and calibration.",
  "example": "Classify sentiment.\nReview: \"Arrived broken.\" -> negative\nReview: \"Works perfectly.\" -> positive\nReview: \"Battery died in a day.\" ->\n",
  "broader": [
    "in-context-learning"
  ],
  "narrower": [
    "exemplar-selection",
    "exemplar-ordering",
    "few-shot-calibration"
  ],
  "related": [
    "zero-shot-prompting",
    "many-shot-in-context-learning"
  ],
  "introduced": 2020,
  "sources": [
    {
      "title": "Language Models are Few-Shot Learners",
      "authors": "Brown et al.",
      "year": 2020,
      "url": "https://arxiv.org/abs/2005.14165"
    }
  ],
  "url": "https://protologue.com/t/few-shot-prompting/",
  "citation": "Protologue. (2026). Few-shot Prompting. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0009). https://protologue.com/t/few-shot-prompting/"
}