AI engineering glossary · Evaluation metrics
What is Token-level F1?
Token-level F1 (also called answer F1, SQuAD F1): An answer-scoring metric for question answering that treats the predicted and reference answers as bags of tokens and computes F1 on their overlap. It gives partial credit when the answer is close but not identical, unlike exact match.
Token-level F1: an example
Reference answer 'the Reserve Bank of India' and prediction 'Reserve Bank of India' share 4 tokens: precision 1.0, recall 0.8, so F1 is about 0.89.
Related terms
More Evaluation metrics terms
- Translation edit rate
- True negative
- True positive
- V-measure
- Weighted averaging
- Weighted kappa
- Word error rate
- Youden's J statistic
Where you learn it
Token-level F1 is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.