用论文总结框架发现大模型在人生叙事中存在种族与性别偏见
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
- 构建基于摘要的分析流程，检测大模型对人生故事的视角偏移
- 实证发现模型在描述不同种族与性别个体时存在系统性偏差
- 适合关注生成内容伦理的研究者或使用LLM做质性分析的团队
越来越多研究探索使用大语言模型（LLMs）加速或扩展文本数据的定性分析。尽管可在演绎编码等任务中直接对比LLM与人工标注的准确性，但在归纳主题分析这类抽象方法中，评估其伦理与有效性更具挑战。我们与心理学家合作，研究LLMs对人生叙事所做的抽象推断，探讨将大模型作为意义解释者如何影响研究结论与视角。提出一种基于摘要的流水线，用于揭示大模型在解读人生故事时可能存在的立场偏见。结果表明该方法可有效识别出种族与性别偏见，存在代表性伤害风险。建议未来涉及大模型对参与者书面文本或转录话语进行解释的研究，采用此分析以刻画研究中的立场画像。
原文摘要 · Abstract (English)
Increasingly, studies are exploring using Large Language Models (LLMs) for accelerated or scaled qualitative analysis of text data. While we can compare LLM accuracy against human labels directly for deductive coding, or labeling text, it is more challenging to judge the ethics and effectiveness of using LLMs in abstractive methods such as inductive thematic analysis. We collaborate with psychologists to study the abstractive claims LLMs make about human life stories, asking, how does using an LLM as an interpreter of meaning affect the conclusions and perspectives of a study? We propose a summarization-based pipeline for surfacing biases in perspective-taking an LLM might employ in interpreting these life stories. We demonstrate that our pipeline can identify both race and gender bias with the potential for representational harm. Finally, we encourage the use of this analysis in future studies involving LLM-based interpretation of study participants' written text or transcribed speech to characterize a positionality portrait for the study.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。