{
  "id": "truthfulqa",
  "code": "PTL-0194",
  "term": "TruthfulQA",
  "aliases": [],
  "category": "benchmarks",
  "definition": "TruthfulQA is a benchmark of questions crafted so that some people would answer them falsely because of common misconceptions, used to measure whether a model repeats popular falsehoods instead of answering truthfully.",
  "description": "Its creators found that larger models of the time were often less truthful, because they imitated human misconceptions in their training data more faithfully. It remains a common reference for truthfulness, though, like other older public benchmarks, it is exposed to data contamination.",
  "example": null,
  "broader": [
    "benchmark"
  ],
  "narrower": [],
  "related": [
    "hallucination",
    "sycophancy",
    "simpleqa"
  ],
  "introduced": 2021,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "TruthfulQA: Measuring How Models Mimic Human Falsehoods",
      "authors": "Lin et al.",
      "year": 2021,
      "url": "https://arxiv.org/abs/2109.07958"
    }
  ],
  "url": "https://protologue.com/t/truthfulqa/",
  "citation": "Protologue. (2026). TruthfulQA. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0194). https://protologue.com/t/truthfulqa/"
}