Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Bogen, Miranda"'
Autor:
Winecoff, Amy A., Bogen, Miranda
Documentation plays a crucial role in both external accountability and internal governance of AI systems. Although there are many proposals for documenting AI data, models, systems, and methods, the ways these practices enhance governance as well as
Externí odkaz:
http://arxiv.org/abs/2409.08960
Autor:
Kapoor, Sayash, Bommasani, Rishi, Klyman, Kevin, Longpre, Shayne, Ramaswami, Ashwin, Cihon, Peter, Hopkins, Aspen, Bankston, Kevin, Biderman, Stella, Bogen, Miranda, Chowdhury, Rumman, Engler, Alex, Henderson, Peter, Jernite, Yacine, Lazar, Seth, Maffulli, Stefano, Nelson, Alondra, Pineau, Joelle, Skowron, Aviya, Song, Dawn, Storchan, Victor, Zhang, Daniel, Ho, Daniel E., Liang, Percy, Narayanan, Arvind
Foundation models are powerful technologies: how they are released publicly directly shapes their societal impact. In this position paper, we focus on open foundation models, defined here as those with broadly available model weights (e.g. Llama 2, S
Externí odkaz:
http://arxiv.org/abs/2403.07918
Autor:
Timmaraju, Aditya Srinivas, Mashayekhi, Mehdi, Chen, Mingliang, Zeng, Qi, Fettes, Quintin, Cheung, Wesley, Xiao, Yihan, Kannadasan, Manojkumar Rangasamy, Tripathi, Pushkar, Gahagan, Sean, Bogen, Miranda, Roudani, Rob
Variances in ad impression outcomes across demographic groups are increasingly considered to be potentially indicative of algorithmic bias in personalized ads systems. While there are many definitions of fairness that could be applicable in the conte
Externí odkaz:
http://arxiv.org/abs/2306.03293
Autor:
Hazirbas, Caner, Bang, Yejin, Yu, Tiezheng, Assar, Parisa, Porgali, Bilal, Albiero, Vítor, Hermanek, Stefan, Pan, Jacqueline, McReynolds, Emily, Bogen, Miranda, Fung, Pascale, Ferrer, Cristian Canton
Developing robust and fair AI systems require datasets with comprehensive set of labels that can help ensure the validity and legitimacy of relevant measurements. Recent efforts, therefore, focus on collecting person-related datasets that have carefu
Externí odkaz:
http://arxiv.org/abs/2211.05809
Autor:
Cai, William, Encarnacion, Ro, Chern, Bobbie, Corbett-Davies, Sam, Bogen, Miranda, Bergman, Stevie, Goel, Sharad
In domains ranging from computer vision to natural language processing, machine learning models have been shown to exhibit stark disparities, often performing worse for members of traditionally underserved groups. One factor contributing to these per
Externí odkaz:
http://arxiv.org/abs/2202.01327
Autor:
Bakalar, Chloé, Barreto, Renata, Bergman, Stevie, Bogen, Miranda, Chern, Bobbie, Corbett-Davies, Sam, Hall, Melissa, Kloumann, Isabel, Lam, Michelle, Candela, Joaquin Quiñonero, Raghavan, Manish, Simons, Joshua, Tannen, Jonathan, Tong, Edmund, Vredenburgh, Kate, Zhao, Jiejing
Many technical approaches have been proposed for ensuring that decisions made by machine learning systems are fair, but few of these proposals have been stress-tested in real-world systems. This paper presents an example of one team's approach to the
Externí odkaz:
http://arxiv.org/abs/2103.06172
Organizations cannot address demographic disparities that they cannot see. Recent research on machine learning and fairness has emphasized that awareness of sensitive attributes, such as race and sex, is critical to the development of interventions.
Externí odkaz:
http://arxiv.org/abs/1912.06171
Autor:
Ali, Muhammad, Sapiezynski, Piotr, Bogen, Miranda, Korolova, Aleksandra, Mislove, Alan, Rieke, Aaron
Publikováno v:
Proceedings of the ACM on Human-Computer Interaction 2019
The enormous financial success of online advertising platforms is partially due to the precise targeting features they offer. Although researchers and journalists have found many ways that advertisers can target---or exclude---particular groups of us
Externí odkaz:
http://arxiv.org/abs/1904.02095
Autor:
Bakalar, Chlo��, Barreto, Renata, Bergman, Stevie, Bogen, Miranda, Chern, Bobbie, Corbett-Davies, Sam, Hall, Melissa, Kloumann, Isabel, Lam, Michelle, Candela, Joaquin Qui��onero, Raghavan, Manish, Simons, Joshua, Tannen, Jonathan, Tong, Edmund, Vredenburgh, Kate, Zhao, Jiejing
Many technical approaches have been proposed for ensuring that decisions made by machine learning systems are fair, but few of these proposals have been stress-tested in real-world systems. This paper presents an example of one team's approach to the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3b515c41b70fab44d370278b01c24868
http://arxiv.org/abs/2103.06172
http://arxiv.org/abs/2103.06172