**Measuring System Performance in Question-Answering Tasks Using EM**

Exact Match (EM) score is a metric commonly used in NLP tasks, particularly in Question Answering systems. It measures the percentage of predictions made by a model that exactly match the target or ground truth answers.

In the context of question answering, an answer is considered to be correct only if it matches the reference answer exactly. The EM score is a straightforward evaluation metric that provides a clear indication of how often a model produces answers that are exactly right.

The formula for EM score is:

$$
\textbf{EM} = \frac{\text{Count of answers predicted exactly}}{\text{Count of answers}}
$$