自动摘要中的政治偏见：特朗普和拜登的案例研究（英文版）

英文标题：Characterizing Political Bias in Automatic Summaries: A Case Study of Trump and Biden中文摘要：该研究使用实体替换方法研究了新闻文章自动生成摘要中对政治家的描绘，发现抽取和生成式摘要模型中川普和拜登的政治偏见存在着差异，该系统性特征提供了未来研究偏见的框架。英文摘要：Growing literature has shown that powerful NLP systems may encode socialbiases; however, the political bias of summarization models remains relativelyunknown. In this work, we use an entity replacement method to investigate theportrayal of politicians in automatically generated summaries of news articles.We develop a