In this paper, we propose the modified UMP beliefpropagation(BP)-based decoding algorithm which utilizes a new normalization factor to diminish the error introduced by approximation of the soft values given by a previously proposed UMP BP-based algorithm. This modified UMP BP-based algorithm shows better in performance than the normalized UMP BP based algorithm i.e it has an error performance closer to BP than that of the normalized UMP BP-based algorithm on the AWGN channel for LDPC codes. Also this algorithm has the same complexity to implement as UMP BP-based algorithm.