arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.12138cs.AIcs.CL
收藏

文本嵌入模型中的偏见

Bias in Text Embedding Models

Vasyl Rakivnenko, Nestor Maslej, Jessica Cervi, Volodymyr Zhukov

AI总结:

本文研究了流行文本嵌入模型的性别偏见问题,发现模型普遍存在性别职业关联偏见,但偏见的表现、程度和方向因模型和提示词而异,提醒企业使用该技术时需注意相关问题。

摘要:

文本嵌入正成为一种日益流行的人工智能方法,在商业领域尤其如此,但文本嵌入模型存在偏见的可能性尚未得到充分认识。本文研究了一批流行的文本嵌入模型的偏见程度,特别是性别维度的偏见。更具体地说,本文研究了这些模型将给定职业列表与性别化词汇相关联的程度。分析表明,文本嵌入模型容易出现性别偏见,但表现形式各不相同。尽管模型间存在某些共性,例如护士、家庭主妇和社交名流等职业与女性标识词的关联度更高,而首席执行官、经理和老板等职业与男性标识词的关联度更高,但并非所有模型对每个职业都有相同的性别关联。此外,偏见的程度和方向性也会因模型而异,并取决于模型被提示使用的特定词汇。本文证明了性别偏见困扰着文本嵌入模型,并建议使用该技术的企业需要注意这一问题的具体维度。

英文摘要:

Text embedding is becoming an increasingly popular AI methodology, especially among businesses, yet the potential of text embedding models to be biased is not well understood. This paper examines the degree to which a selection of popular text embedding models are biased, particularly along gendered dimensions. More specifically, this paper studies the degree to which these models associate a list of given professions with gendered terms. The analysis reveals that text embedding models are prone to gendered biases but in varying ways. Although there are certain inter-model commonalities, for instance, greater association of professions like nurse, homemaker, and socialite with female identifiers, and greater association of professions like CEO, manager, and boss with male identifiers, not all models make the same gendered associations for each occupation. Furthermore, the magnitude and directionality of bias can also vary on a model-by-model basis and depend on the particular words models are prompted with. This paper demonstrates that gender bias afflicts text embedding models and suggests that businesses using this technology need to be mindful of the specific dimensions of this problem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑