Summarization is an important application of large language models (LLMs). Most previous evaluation of summarization models has focused on their performance in content selection, faithfulness, grammaticality and coherence. However, it is well known that LLMs reproduce and reinforce harmful social biases. This raises the question: Do these biases affect model outputs in a relatively constrained setting like summarization? To help answer this question, we first motivate and introduce a number of definitions for biased behaviours in summarization models, along with practical operationalizations. Since we find that biases inherent to input documents can confound bias analysis in summaries, we propose a method to generate input documents with carefully controlled demographic attributes. This allows us to study summarizer behavior in a controlled setting, while still working with realistic input documents. Finally, we measure gender bias in English summaries generated by both purpose-built summarization models and general purpose chat models as a case study. We find content selection in single document summarization to be largely unaffected by gender bias, while hallucinations exhibit evidence of downstream biases in summarization.

翻译：摘要是大型语言模型（LLM）的重要应用。以往对摘要模型的评估主要聚焦于内容选择、忠实度、语法正确性和连贯性等维度。然而，众所周知，LLM会复制并强化有害的社会偏见。这引发了一个问题：在摘要这类相对受限的场景中，这些偏见是否会影响模型输出？为解答此问题，我们首先提出并阐释了摘要模型中若干偏见行为的定义及其可操作化实践方案。鉴于输入文档固有的偏见会干扰摘要中的偏见分析，我们提出了一种通过精细控制人口统计属性来生成输入文档的方法，从而在保持输入文档真实性的同时，能够在受控条件下研究摘要器的行为。最后，我们以英语摘要为案例，对专用摘要模型与通用对话模型生成的摘要进行了性别偏见度量。研究发现，单文档摘要的内容选择基本不受性别偏见影响，而模型幻觉现象则揭示了摘要过程中下游偏见的证据。