论文标题
忠于文件还是世界？通过抽象摘要中的实体联系知识来缓解幻觉
Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization
论文作者
论文摘要
尽管抽象性摘要最近取得了进步，但当前的汇总系统仍然遭受内容幻觉的困扰，在这些幻觉中，模型产生与源文档无关或矛盾的文本。但是，先前的工作是基于以下假设：任何未明确出现在源中的生成事实都是不希望的幻觉。已经提出了通过最终将“忠诚”提高到源文档来解决这种情况的方法，但实际上，黄金参考目标中有很大一部分实体并非直接在源中。在这项工作中，我们表明这些实体不是畸变，而是需要利用外部世界知识来推断源实体的推理路径。我们表明，通过利用外部知识基础，我们可以提高摘要的忠诚，而不仅仅是使它们更具挖掘性，而且我们表明，与来源相关的外部知识基础可以使生成的摘要的事实受益。
Despite recent advances in abstractive summarization, current summarization systems still suffer from content hallucinations where models generate text that is either irrelevant or contradictory to the source document. However, prior work has been predicated on the assumption that any generated facts not appearing explicitly in the source are undesired hallucinations. Methods have been proposed to address this scenario by ultimately improving `faithfulness' to the source document, but in reality, there is a large portion of entities in the gold reference targets that are not directly in the source. In this work, we show that these entities are not aberrations, but they instead require utilizing external world knowledge to infer reasoning paths from entities in the source. We show that by utilizing an external knowledge base, we can improve the faithfulness of summaries without simply making them more extractive, and additionally, we show that external knowledge bases linked from the source can benefit the factuality of generated summaries.
