Entity abstract summarization aims to generate a coherent description of a
given entity based on a set of relevant Internet documents. Pretrained language
models (PLMs) have achieved significant success in this task, but they may
suffer from hallucinations, i.e. generating non-factual information about the
entity. To address this issue, we decompose the summary into two components:
Facts that represent the factual information about the given entity, which PLMs
are prone to fabricate; and Template that comprises generic content with
designated slots for facts, which PLMs can generate competently. Based on the
facts-template decomposition, we propose SlotSum, an explainable framework for
entity abstract summarization. SlotSum first creates the template and then
predicts the fact for each template slot based on the input documents.
Benefiting from our facts-template decomposition, SlotSum can easily locate
errors and further rectify hallucinated predictions with external knowledge. We
construct a new dataset WikiFactSum to evaluate the performance of SlotSum.
Experimental results demonstrate that SlotSum could generate summaries that are
significantly more factual with credible external knowledge.

基于预训练语言模型的实体摘要生成过程中，常常出现虚构信息的问题，为了解决这个问题，我们使用事实和模板的分解结构，提出了一种可解释的框架 SlotSum。该框架首先创建一个模板，然后根据输入文档预测每个模板位置的事实。通过事实和模板的分解，SlotSum 能够容易地定位错误并利用外部知识修正虚构的预测结果。我们构建了一个新的数据集 WikiFactSum 用于评估 SlotSum 的性能，实验结果表明 SlotSum 能够生成更具可信度和事实性的摘要。