The number of published scientific articles is increasing at an exponential rate per year. Consequently, their claimed contributions may overlap, which is difficult to identify until the reader has reviewed all the works. To optimize the effort in conducting literature reviews for research, e.g., in the field of power engineering, there is a need to develop a tool that can quantitatively assess the contributions of scientific articles. Leveraging the advancements in transformer-based learning algorithms, this project seeks to develop a tool that will evaluatethe quality of a given article.