{
  "id": "instruction-tuning",
  "code": "PTL-0010",
  "term": "Instruction Tuning",
  "aliases": [
    "instruction fine-tuning",
    "supervised fine-tuning",
    "SFT"
  ],
  "category": "foundations",
  "definition": "Instruction tuning is fine-tuning a pretrained language model on many tasks phrased as natural-language instructions, so that it follows unseen instructions zero-shot.",
  "description": "The FLAN work showed that tuning on dozens of instruction-formatted datasets substantially improved zero-shot performance on held-out tasks. Combined with reinforcement learning from human feedback, it produced the instruction-following chat models that most prompting techniques now target.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "zero-shot-prompting",
    "rlhf"
  ],
  "introduced": 2021,
  "sources": [
    {
      "title": "Finetuned Language Models Are Zero-Shot Learners",
      "authors": "Wei et al.",
      "year": 2021,
      "url": "https://arxiv.org/abs/2109.01652"
    },
    {
      "title": "Training language models to follow instructions with human feedback",
      "authors": "Ouyang et al.",
      "year": 2022,
      "url": "https://arxiv.org/abs/2203.02155"
    }
  ],
  "url": "https://protologue.com/t/instruction-tuning/",
  "citation": "Protologue. (2026). Instruction Tuning. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0010). https://protologue.com/t/instruction-tuning/"
}