We introduce HOVER (HOppy VERification), a dataset for many-hop evidence extraction and fact verification. It challenges models to extract facts from several Wikipedia articles that are relevant to a claim and classify whether the claim is SUPPORTED or NOT-SUPPORTED by the facts. In HOVER, the claims require evidence to be extracted from as many as four English Wikipedia articles and embody reasoning graphs of diverse shapes. Moreover, most of the 3/4-hop claims are written in multiple

more »

... , which adds to the complexity of understanding long-range dependency relations such as coreference. We show that the performance of an existing stateof-the-art semantic-matching model degrades significantly on our dataset as the number of reasoning hops increases, hence demonstrating the necessity of many-hop reasoning to achieve strong results. We hope that the introduction of this challenging dataset and the accompanying evaluation task will encourage research in many-hop fact retrieval and information verification. 1 * Equal contribution. 1 We make HoVer dataset publicly available at https://hover-nlp.github.io