研究大模型标注中性别偏见来源，发现内容比人口特征影响更大。
Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation
- 用混合模型分析标注差异，发现人口因素仅贡献8%方差。
- 提示大模型使用人格设定反而降低与人工判断的一致性。
- 模型解释显示其依赖具体文本关键词，而非人口属性。
理解标注变异的来源对构建公平的自然语言处理系统至关重要，尤其在性别歧视检测等涉及人口偏见的任务中。本研究通过广义线性混合模型，量化了标注者人口特征与文本内容对标注决策的影响。结果显示，尽管人口因素具有统计显著性，但仅解释了8%的方差，文本内容才是主导因素。随后评估生成式AI作为标注者的可靠性，考察通过赋予其人口角色提示是否能提升与人类判断的一致性。结果表明，简单的角色提示常无法提升性能，甚至导致下降。此外，可解释AI技术揭示，模型预测主要依赖与性别歧视相关的特定文本标记，而非人口特征相关线索。因此，我们主张应聚焦内容驱动的解释和稳健的标注流程，而非尝试模拟人口特征。
原文摘要 · Abstract (English)
Understanding the sources of variability in annotations is crucial for developing fair NLP systems, especially for tasks like sexism detection where demographic bias is a concern. This study investigates the extent to which annotator demographic features influence labeling decisions compared to text content. Using a Generalized Linear Mixed Model, we quantify this inf luence, finding that while statistically present, demographic factors account for a minor fraction ( 8%) of the observed variance, with tweet content being the dominant factor. We then assess the reliability of Generative AI (GenAI) models as annotators, specifically evaluating if guiding them with demographic personas improves alignment with human judgments. Our results indicate that simplistic persona prompting often fails to enhance, and sometimes degrades, performance compared to baseline models. Furthermore, explainable AI (XAI) techniques reveal that model predictions rely heavily on content-specific tokens related to sexism, rather than correlates of demographic characteristics. We argue that focusing on content-driven explanations and robust annotation protocols offers a more reliable path towards fairness than potentially persona simulation.
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。