Outliers in regression are data points that are significantly different from the other observations in the dataset. They are values that fall far away from the trend established by the rest of the data, which can distort the results of the regression analysis. Outliers can result from variability in the data, measurement errors, or they may indicate an unusual or special case. Because they can influence the slope and intercept of the regression line, it's important to identify and assess their impact on the overall model to ensure accurate predictions and conclusions.