Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social biases from the data on which they are trained. In this paper, we present evidence of such undesirable biases towards mentions of disability in two different English language models: toxicity prediction and sentiment analysis. Next, we demonstrate that the neural embeddings that are the critical first step in most NLP pipelines similarly contain undesirable biases towards mentions of disability. We end by highlighting topical biases in the discourse about disability which may contribute to the observed model biases; for instance, gun violence, homelessness, and drug addiction are over-represented in texts discussing mental illness.
Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual Disabilities
University of Zurich（苏黎世大学）；EPFL（瑞士联邦理工学院）；Zurich University of Applied Sciences（苏黎世应用科学大学）
Digital Comprehensibility Assessment of Simplified Texts among Persons with Intellectual Disabilities
University of Zurich（苏黎世大学）；University of Teacher Education in Special Needs Zurich（苏黎世特殊教育师范大学）；Johannes Gutenberg University Mainz（美因茨约翰内斯·古滕贝格大学）；Klinikum rechts der Isar, Technische Universität München（慕尼黑工业大学 rechts der Isar 医院）
Leveraging ChatGPT and Other NLP Methods for Identifying Risk and Protective Behaviors in MSM: Social Media and Dating apps Text Analysis
1 Department of Computer Science, Henry Samueli School of Engineering, University of California, Los Angeles, Los Angeles, CA；2 Department of Social Welfare, Luskin School of Public Affairs, University of California, Los Angeles, Los Angeles, CA；3 Department of Counseling \& Educational Psychology, New Mexico State University, Las Cruces, NM
German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies
University of Mannheim（曼海姆大学）；GESIS -- Leibniz Institute for the Social Sciences（莱布尼茨社会科学研究所）；RWTH Aachen University（亚琛工业大学）；Complexity Science Hub（复杂性科学中心）
Shiny Stories, Hidden Struggles: Investigating the Representation of Disability Through the Lens of LLMs
Department of Foreign Languages and Literature, University of Verona（外国语言文学系，威尼斯大学）；Department of Information Engineering and Computer Science, University of Trento（信息工程与计算机科学系，特伦托大学）；Data and Web Science Group, University of Mannheim（数据与网络科学小组，曼海姆大学）
Associations Between Natural Language Processing (NLP) Enriched Social Determinants of Health and Suicide Death among US Veterans
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；McGill University（麦吉尔大学）；University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；University of Connecticut（康涅狄格大学）；Uconn Health（康涅狄格大学健康中心）；University of Massachusetts Chan Medical School（马萨诸塞大学陈医学院）；Veterans Affairs Bedford Healthcare System（退伍军人事务部贝德福德医疗系统）；United States Department of Veterans Affairs（美国退伍军人事务部）；University of Texas Health Science Center at Houston（德克萨斯大学休斯顿健康科学中心）
A Case Report On The "A.I. Locked-In Problem": social concerns with modern NLP
Institute for Management and Digitalization IMD（管理与数字化研究所（IMD））；Kalaidos University of Applied Sciences（卡拉多斯应用科学大学）；Laboratory for Cognitive Neuroscience LCNS（认知神经科学实验室（LCNS））；University of Fribourg（弗里堡大学）；Translational Research Center（转化研究中心）；University Hospital for Psychiatry Bern（伯尔尼大学精神病院）
