Glossary term
Glossary term
Agentic Systems
An expert's response to a prompt. For example, given the following prompt:
Translate the question "What is your name?" from English to French.
An expert's response might be:
Comment vous appelez-vous?
Various metrics (such as ROUGE) measure the degree to which the reference text matches an ML model's generated text.
Note: The expert is typically a human but could be an ML model.
Created for this library
An LLM evaluation team uses reference texts written by domain experts to grade generated outputs against high-quality answers.
A translation evaluation team uses reference translations from professional translators as the ground truth for BLEU and BLEURT scoring.
A summarization team uses reference summaries from editors to grade generated summaries on ROUGE.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License