This isn't completely clear to me. Say you have a massive passage that you want your LSTM to learn off of, how is it making sure it doesnt remove details from the first paragraph?
I believe this paper will be of help. It explains the backpropagation algorithm.
Also note that for LSTM's that process passages, multiple LSTM blocks are used in a sequential and parallel manner. And additionally, neural networks are black boxes: we don't know how the work internally, and they make up which details are important themselves.