Seamful XAI: Operationalizing Seamful Design in Explainable AI

Autor: Ehsan, Upol, Liao, Q. Vera, Passi, Samir, Riedl, Mark O., Daume III, Hal

Publikováno v: ACM CSCW 2024

Mistakes in AI systems are inevitable, arising from both technical limitations and sociotechnical gaps. While black-boxing AI systems can make the user experience seamless, hiding the seams risks disempowering users to mitigate fallouts from AI mista

Externí odkaz: http://arxiv.org/abs/2211.06753

'From What I see, this makes sense': Seeing meaning in algorithmic results

Autor: Passi, Samir, Sengers, Phoebe

In this workshop paper, we use an empirical example from our ongoing fieldwork, to showcase the complexity and situatedness of the process of making sense of algorithmic results; i.e. how to evaluate, validate, and contextualize algorithmic outputs.

Externí odkaz: http://arxiv.org/abs/2102.07844

Data Vision: Learning to See Through Algorithmic Abstraction

Autor: Passi, Samir, Jackson, Steven J.

Publikováno v: In Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. ACM, New York, NY, USA, 2436-2447

Learning to see through data is central to contemporary forms of algorithmic knowledge production. While often represented as a mechanical application of rules, making algorithms work with data requires a great deal of situated work. This paper exami

Externí odkaz: http://arxiv.org/abs/2002.03387

Mapping EINS -- An exercise in mapping the Network of Excellence in Internet Science

Autor: Salah, Almila Akdag, Wyatt, Sally, Passi, Samir, Scharnhorst, Andrea

Publikováno v: Conference Proceedings of the First International Conference on Internet Science, April 9-11, 2013 Brussels. Pages 75-78

This paper demonstrates the application of bibliometric mapping techniques in the area of funded research networks. We discuss how science maps can be used to facilitate communication inside newly formed communities, but also to account for their act

Externí odkaz: http://arxiv.org/abs/1304.5753

The Who in Explainable AI: How AI Background Shapes Perceptions of AI Explanations

Autor: Ehsan, Upol, Passi, Samir, Liao, Q. Vera, Chan, Larry, Lee, I-Hsiang, Muller, Michael, Riedl, Mark O.

Explainability of AI systems is critical for users to take informed actions and hold systems accountable. While "opening the opaque box" is important, understanding who opens the box can govern if the Human-AI interaction is effective. In this paper,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95fc5a0384defebc8c541d74df3a0ba5