{
  "id": "confidence-calibration",
  "code": "PTL-0121",
  "term": "Confidence Calibration",
  "aliases": [
    "calibration",
    "verbalized confidence",
    "uncertainty estimation"
  ],
  "category": "verification",
  "definition": "Confidence calibration is the degree to which a model's expressed or implied confidence matches how often it is actually right; a well-calibrated model that says it is 80% sure is correct about 80% of the time.",
  "description": "Confidence can be read from token probabilities, by asking the model to state a confidence (verbalized confidence), or by sampling several answers and measuring agreement. Studies have found pretrained models fairly well calibrated on suitably formatted multiple-choice questions, and that for instruction-tuned models verbalized confidence can be better calibrated than token probabilities. Calibration lets an application abstain or escalate when the model is unsure. It is different from few-shot calibration, which corrects label bias in prompts.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "log-probabilities",
    "hallucination",
    "selfcheckgpt",
    "few-shot-calibration"
  ],
  "introduced": null,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Language Models (Mostly) Know What They Know",
      "authors": "Kadavath et al.",
      "year": 2022,
      "url": "https://arxiv.org/abs/2207.05221"
    },
    {
      "title": "Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback",
      "authors": "Tian et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2305.14975"
    }
  ],
  "url": "https://protologue.com/t/confidence-calibration/",
  "citation": "Protologue. (2026). Confidence Calibration. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0121). https://protologue.com/t/confidence-calibration/"
}