Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender:profession or race:crime. This narrow scope often overlooks a vast range of unexamined implicit associations, restricting the identification and, hence, mitigation of such biases. We address this gap by probing VLMs to (1) uncover hidden, implicit associations across 9 bias dimensions. We systematically explore diverse input and output modalities and (2) demonstrate how biased associations vary in their negativity, toxicity, and extremity. Our work (3) identifies subtle and extreme biases that are typically not recognized by existing methodologies. We make the Dataset of retrieved associations, (Dora), publicly available here https://github.com/chahatraj/BiasDora.
Co-occurrence is not Factual Association in Language Models
Department of Electronics Engineering(电子工程系);Tsinghua University(清华大学);Department of Electronics Engineering, College of AI(人工智能学院电子工程系);Beijing National Research Center for Information Science and Technology(北京信息科学国家研究中心);Center for Big Data and Clinical Research, Institute for Precision Medicine(精准医学研究院大数据与临床研究中心)
Contrastive Analysis of Linguistic Representations in Large Language Model Outputs through Structured Synthetic Data Generation and Abstracted N-gram Associations
Seeds of Stereotypes: A Large-Scale Textual Analysis of Race and Gender Associations with Diseases in Online Sources
Aarhus University(奥胡斯大学);Massachusetts Institute of Technology(麻省理工学院);University of Alberta(阿尔伯塔大学);University of Manitoba(曼尼托巴大学);Mbarara University of Science and Technology(姆巴拉拉科技大学);Fundacion Arturo Lopez Perez(阿图罗·洛佩斯·佩雷斯基金会);Mass General Brigham(麻省总医院布里格姆);Harvard Medical School(哈佛医学院);Dana-Farber Cancer Institute(丹娜-法伯癌症研究所);Emory University School of Medicine(埃默里大学医学院);Beth Israel Deaconess Medical Center(贝斯以色列女执事医疗中心);Harvard T.H. Chan School of Public Health(哈佛大学陈曾熙公共卫生学院)
本文通过分析 Arxiv、Wikipedia 和 Common Crawl 中18种疾病与种族、性别术语的共现,并对比患病率与 GPT-4 输出,揭示在线文本及 LLM 预训练数据中的人口统计学偏见。
Debiased Large Language Models Still Associate Muslims with Uniquely Violent Acts
Beckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校贝克曼高级科学技术研究所);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
University of Southern California(南加州大学);Information Sciences Institute(信息科学研究所);Amazon Alexa(亚马逊Alexa);Harvard University(哈佛大学);University of California, Los Angeles(加州大学洛杉矶分校)
Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
Knight Foundation School of Computing and Information Sciences(骑士基金会计算与信息科学学院);Florida International University(佛罗里达国际大学);College of Engineering(工程学院);University of South Florida(佛罗里达州立大学)