{
  "id": "many-shot-in-context-learning",
  "code": "PTL-0022",
  "term": "Many-shot In-Context Learning",
  "aliases": [
    "many-shot ICL",
    "long-context ICL"
  ],
  "category": "exemplars",
  "definition": "Many-shot in-context learning places hundreds or thousands of demonstrations in a long-context prompt, often yielding large gains over few-shot prompting.",
  "description": "Agarwal et al. found consistent improvements as the number of shots grew into the hundreds, and introduced variants that use model-generated rationales or unlabeled problems. The same scaling behavior underlies the many-shot jailbreaking attack.",
  "example": null,
  "broader": [
    "in-context-learning"
  ],
  "narrower": [],
  "related": [
    "few-shot-prompting",
    "many-shot-jailbreaking",
    "context-window"
  ],
  "introduced": 2024,
  "sources": [
    {
      "title": "Many-Shot In-Context Learning",
      "authors": "Agarwal et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2404.11018"
    }
  ],
  "url": "https://protologue.com/t/many-shot-in-context-learning/",
  "citation": "Protologue. (2026). Many-shot In-Context Learning. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0022). https://protologue.com/t/many-shot-in-context-learning/"
}