Summary: The empirical likelihood is a versatile nonparametric approach to testing hypotheses and constructing confidence regions. However it is not clear if Wilks' theorem still works in high dimensions. In this paper, by adding two pseudo-observations to the original data set, we prove the asymptotic normality of the log empirical likelihood-ratio statistic when the sample size and the data dimension are comparable. In practice, we suggest using the normalized \(F(p,n-p)\) distribution to approximate its distribution. Simulation results show excellent performance of this approximation.