10 papers
Studying People to Study AI: Expert Perspectives on the Epistemic Fit and Barriers of Human Research in AI Safety & Ethics
Jessica Y. Bo, Paula Akemi Aoyagui, Shalaleh Rismani +3
Safety risks of AI are becoming increasingly evident in human interactions with AI technologies. The prominent approaches to evaluating these risks favor technical methods, such as…
Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communities
Dipto Das, Achhiya Sultana, Ankit Singh Chauhan +5
Language operates as a mechanism of both marginalization and resistance, especially for minority communities navigating insensitive and harmful speech online. As content moderation…
"Is This Not Enough?": Asymmetries in Institutional Accountability and Collective Sensemaking in the Case of Canada's Algorithmic Visa Triage System
Dipto Das, Matthew Tamura, Syed Ishtiaque Ahmed +1
This paper examines how algorithmic accountability in Canada's visa system is articulated institutionally and experienced by applicants across borders. We analyzed Immigration, Ref…
How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language
Dipto Das, Shion Guha, Bryan Semaan
Sociotechnical systems, such as language technologies, frequently exhibit identity-based biases. These biases exacerbate the experiences of historically marginalized communities an…
Beyond Categories of Caste: Examining Caste Bias and Morality in Text-to-Image AI Models
Divyanshu Kumar Singh, Dipto Das, Deepika Rama Subramanian +3
Text-to-Image (T2I) models have shown promising utility across various domains. However, such models are also amplifying harmful societal biases in their outputs. In the context of…
Fairness Audits of Institutional Risk Models in Deployed ML Pipelines
Kelly McConvey, Dipto Das, Maya Ghai +3
Fairness audits of institutional risk models are critical for understanding how deployed machine learning pipelines allocate resources. Drawing on multi-year collaboration with Cen…