With the ever-increasing amount of textual information available, it is becoming increasingly unlikely that a single document will provide the answer to a question. A more likely scenario is that multiple documents will each propose answers. Current question-answering systems rarely resolve redundant or contradictory information when answering questions. This is a problem in the biomedical community where multiple documents often attempt to answer a question. The multi-layer question answering approach proposed in this position paper was inspired by a study of scientists in public health and medicine as they used the medical literature to answer research questions. The proposed approach, called Information Synthesis (IS), takes advantage of existing question answering techniques to extract facts from biomedical literature then incorporates formal meta-analysis techniques to unify contradictory findings. This approach is based on the premise that the person posing the question has know...