Generated text is text produced by a machine learning model, especially a language model. It may be evaluated against reference text, ground truth, or task-specific criteria such as factuality, fluency, relevance, and safety.
In general, the text that an ML model outputs. When evaluating large language models, some metrics compare generated text against reference text. For example, suppose you are trying to determine how effectively an ML model translates from French to Dutch. In this case: - The generated text is the Dutch translation that the ML model outputs. - The reference text is the Dutch translation that a human translator (or software) creates. Note that some evaluation strategies don't involve reference text.