{
  "id": "data-contamination",
  "code": "PTL-0178",
  "term": "Data Contamination",
  "aliases": [
    "benchmark contamination",
    "test set contamination",
    "training data leakage"
  ],
  "category": "failure-modes",
  "definition": "Data contamination is the presence of benchmark or test examples in a model's training data, which inflates its measured performance because it may have memorized the answers.",
  "description": "Since models are trained on large web crawls, public benchmarks often leak into training sets. Contamination can be detected, for example, by prompting a model to complete the beginning of test instances and checking for verbatim matches. For application evaluations, the safeguard is a private, regularly refreshed test set.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "evals",
    "knowledge-cutoff"
  ],
  "introduced": 2023,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Time Travel in LLMs: Tracing Data Contamination in Large Language Models",
      "authors": "Golchin and Surdeanu",
      "year": 2023,
      "url": "https://arxiv.org/abs/2308.08493"
    }
  ],
  "url": "https://protologue.com/t/data-contamination/",
  "citation": "Protologue. (2026). Data Contamination. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0178). https://protologue.com/t/data-contamination/"
}