Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning

Has there been real progress in multi-hop question-answering? Models often exploit dataset artifacts to produce correct answers, without connecting information across multiple supporting facts. This limits our ability to measure true progress and defeats the purpose of building multihop QA datasets. We make three contributions towards addressing this. First, we formalize such undesirable behavior as disconnected reasoning across subsets of supporting facts. This allows developing a model-agnostic probe for measuring how much any model can cheat via disconnected reasoning. Second, using a notion of contrastive support sufficiency, we introduce an automatic transformation of existing datasets that reduces the amount of disconnected reasoning. Third, our experiments demonstrate that there hasn't been much progress in multifact reasoning. For a recent large-scale model (XLNet), we show that only 18% of its answer score is obtained through multifact reasoning, roughly the same as that of a simpler RNN baseline. Our transformation shows a substantial reduction in disconnected reasoning (nearly 19 points in answer F1). It is complementary to adversarial approaches, yielding further reductions in conjunction.