Text summarization models have typically focused on optimizing aspects of quality such as fluency, relevance, and coherence, particularly in the context of news articles. However, summarization models are increasingly being used to summarize diverse sources of text, such as social media data, that encompass a wide demographic user base. It is thus crucial to assess not only the quality of the generated summaries, but also the extent to which they can fairly represent the opinions of diverse social groups. Position bias, a long-known issue in news summarization, has received limited attention in the context of social multi-document summarization. We deeply investigate this phenomenon by analyzing the effect of group ordering in input documents when summarizing tweets from three distinct linguistic communities: African-American English, Hispanic-aligned Language, and White-aligned Language. Our empirical analysis shows that although the textual quality of the summaries remains consistent regardless of the input document order, in terms of fairness, the results vary significantly depending on how the dialect groups are presented in the input data. Our results suggest that position bias manifests differently in social multi-document summarization, severely impacting the fairness of summarization models.

翻译：文本摘要模型通常侧重于优化流畅性、相关性和连贯性等质量方面，特别是在新闻文章语境中。然而，摘要模型日益被用于总结多种文本来源（例如社交媒体数据），这些数据涵盖了广泛的用户群体。因此，评估生成摘要的质量，以及它们在多大程度上能公平代表不同社会群体的观点，变得至关重要。位置偏差（新闻摘要中长期存在的问题）在社会多文档摘要的语境中受到的关注有限。我们通过分析输入文档中群体排序的影响，深入研究了这一现象，总结了来自三个不同语言社区的推文：非裔美国英语、西班牙裔相关语言和白人相关语言。我们的实证分析表明，尽管摘要的文本质量在输入文档顺序不变的情况下保持一致，但在公平性方面，结果却因方言群体在输入数据中的呈现方式而有显著差异。我们的结果表明，位置偏差在社会多文档摘要中的表现有所不同，严重影响了摘要模型的公平性。