Proceedings of the ... Conference on Fairness, Accountability, and Transparency最新文献

{"title":"A pipeline for enabling path-specific causal fairness in observational health data.","authors":"Aparajita Kashyap, Sara Matijevic, Noémie Elhadad, Steven A Kushner, Shalmali Joshi","doi":"10.1145/3805689.3806507","DOIUrl":"10.1145/3805689.3806507","url":null,"abstract":"<p><p>When training machine learning (ML) models for potential deployment in a healthcare setting, it is essential to ensure that they do not replicate or exacerbate existing healthcare biases. Although many definitions of fairness exist, we focus on <i>path-specific causal fairness</i>, which allows us to better consider the social and medical contexts in which biases occur (e.g., direct discrimination by a clinician or model versus bias due to differential access to the healthcare system) and to characterize how these biases may appear in learned models. In this work, we map the structural fairness model to the observational healthcare setting and create a generalizable pipeline for training causally fair models. The pipeline explicitly considers specific healthcare context and disparities to define a target \"fair\" model. Our work fills two major gaps: first, we expand on characterizations of the \"fairness-accuracy\" tradeoff by detangling direct and indirect sources of bias, assessing them jointly with model accuracy and the known broader context of biases. Second, we demonstrate how a foundation model trained without fairness constraints on observational health data can be leveraged to generate causally fair downstream predictions in tasks with known social and medical disparities. This work presents a model-agnostic pipeline for training causally fair machine learning models that address both direct and indirect forms of healthcare bias.</p>","PeriodicalId":524095,"journal":{"name":"Proceedings of the ... Conference on Fairness, Accountability, and Transparency","volume":"2026 ","pages":"2952-2979"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13309187/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148348795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"When Testing AI Tests Us: Safeguarding Mental Health on the Digital Frontlines.","authors":"Sachin R Pendse, Darren Gergle, Rachel Kornfield, Jonah Meyerhoff, David Mohr, Jina Suh, Annie Wescott, Casey Williams, Jessica Schleider","doi":"10.1145/3715275.3732120","DOIUrl":"10.1145/3715275.3732120","url":null,"abstract":"<p><p>The systematic testing of generative artificial intelligence (AI) models by collaborative teams and distributed individuals, often called red-teaming, is a core part of the infrastructure that ensures that AI models do not produce harmful content. Unlike past technologies, the black box nature of generative AI systems necessitates a uniquely interactional mode of testing, one in which individuals on red teams actively interact with the system, leveraging natural language to simulate malicious actors and solicit harmful outputs. This <i>interactional labor</i> done by red teams can result in mental health harms that are uniquely tied to the adversarial engagement strategies necessary to effectively red team. The importance of ensuring that generative AI models do not propagate societal or individual harm is widely recognized-one less visible foundation of end-to-end AI safety is also the protection of the mental health and wellbeing of those who work to keep model outputs safe. In this paper, we argue that the unmet mental health needs of AI red-teamers are a critical workplace safety concern. Through analyzing the unique mental health impacts associated with the labor done by red teams, we propose potential individual and organizational strategies that could be used to meet these needs, and safeguard the mental health of red-teamers. We develop our proposed strategies through drawing parallels between common red-teaming practices and interactional labor common to other professions (including actors, mental health professionals, conflict photographers, and content moderators), describing how individuals and organizations within these professional spaces safeguard their mental health given similar psychological demands. Drawing on these protective practices, we describe how safeguards could be adapted for the distinct mental health challenges experienced by red teaming organizations as they mitigate emerging technological risks on the new digital frontlines. <b>Note: This work includes descriptions of violence, trauma, and mental illness.</b></p>","PeriodicalId":524095,"journal":{"name":"Proceedings of the ... Conference on Fairness, Accountability, and Transparency","volume":"2025 ","pages":"1793-1804"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13270898/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148274600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}