Data and feature engineering · MLD-1254

Train-test contamination

Overlap or information transfer between training data and evaluation examples that compromises independence.

Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.

Original example

A benchmark answer appears in pretraining text.

Original caveat

Related examples can contaminate even without exact copies.

Context and aliases

Level: Intermediate. Stages: Data · Training · Evaluation.

Tags: ML · DL · SLM · LLM.

Aliases: Benchmark contamination.

Related concepts

Concepts linking here

Original references

Open original record, export or annotate →