Search for: All records

Critical AI literacy enables understanding of the limitations of AI. In this work, we investigated how Black girls (N=11, ages 9-12) critically engaged with generative AI (genAI) through exploring ChatGPT’s limitations. Learners used various approaches and leveraged their funds of knowledge (e.g., knowledge of pop culture) to investigate where genAI did not perform satisfactorily. We discuss how taking an asset-based approach can support critical AI literacy. 

Public sector leverages artificial intelligence (AI) to enhance the efficiency, transparency, and accountability of civic operations and public services. This includes initiatives such as predictive waste management, facial recognition for identification, and advanced tools in the criminal justice system. While public-sector AI can improve efficiency and accountability, it also has the potential to perpetuate biases, infringe on privacy, and marginalize vulnerable groups. Responsible AI (RAI) research aims to address these concerns by focusing on fairness and equity through participatory AI. We invite researchers, community members, and public sector workers to collaborate on designing, developing, and deploying RAI systems that enhance public sector accountability and transparency. Key topics include raising awareness of AI's impact on the public sector, improving access to AI auditing tools, building public engagement capacity, fostering early community involvement to align AI innovations with public needs, and promoting accessible and inclusive participation in AI development. The workshop will feature two keynotes, two short paper sessions, and three discussion-oriented activities. Our goal is to create a platform for exchanging ideas and developing strategies to design community-engaged RAI systems while mitigating the potential harms of AI and maximizing its benefits in the public sector. 

There has been growing recognition of the crucial role users, especially those from marginalized groups, play in uncovering harmful algorithmic biases. However, it remains unclear how users’ identities and experiences might impact their rating of harmful biases. We present an online experiment (N=2,197) examining these factors: demographics, discrimination experiences, and social and technical knowledge. Participants were shown examples of image search results, including ones that previous literature has identified as biased against marginalized racial, gender, or sexual orientation groups. We found participants from marginalized gender or sexual orientation groups were more likely to rate the examples as more severely harmful. Belonging to marginalized races did not have a similar pattern. Additional factors affecting users’ ratings included discrimination experiences, and having friends or family belonging to marginalized demographics. A qualitative analysis offers insights into users' bias recognition, and why they see biases the way they do. We provide guidance for designing future methods to support effective user-driven auditing. 

Youth regularly use technology driven by artificial intelligence (AI). However, it is increasingly well-known that AI can cause harm on small and large scales, especially for those underrepresented in tech fields. Recently, users have played active roles in surfacing and mitigating harm from algorithmic bias. Despite being frequent users of AI, youth have been under-explored as potential contributors and stakeholders to the future of AI. We consider three notions that may be at the root of youth facing barriers to playing an active role in responsible AI, which are youth (1) cannot understand the technical aspects of AI, (2) cannot understand the ethical issues around AI, and (3) need protection from serious topics related to bias and injustice. In this study, we worked with youth (N = 30) in first through twelfth grade and parents (N = 6) to explore how youth can be part of identifying algorithmic bias and designing future systems to address problematic technology behavior. We found that youth are capable of identifying and articulating algorithmic bias, often in great detail. Participants suggested different ways users could give feedback for AI that reflects their values of diversity and inclusion. Youth who may have less experience with computing or exposure to societal structures can be supported by peers or adults with more of this knowledge, leading to critical conversations about fairer AI. This work illustrates youths' insights, suggesting that they should be integrated in building a future of responsible AI.