Zobrazeno 1 - 10
of 73
pro vyhledávání: '"Balayn, P."'
Autor:
Balayn, Agathe, Pi, Yulu, Widder, David Gray, Alfrink, Kars, Yurrita, Mireia, Upadhyay, Sohini, Karusala, Naveena, Lyons, Henrietta, Turkay, Cagatay, Tessono, Christelle, Attard-Frost, Blair, Gadiraju, Ujwal
This workshop will grow and consolidate a community of interdisciplinary CSCW researchers focusing on the topic of contestable AI. As an outcome of the workshop, we will synthesize the most pressing opportunities and challenges for contestability alo
Externí odkaz:
http://arxiv.org/abs/2408.01051
Explainability and transparency of AI systems are undeniably important, leading to several research studies and tools addressing them. Existing works fall short of accounting for the diverse stakeholders of the AI supply chain who may differ in their
Externí odkaz:
http://arxiv.org/abs/2405.16311
With the widespread proliferation of AI systems, trust in AI is an important and timely topic to navigate. Researchers so far have largely employed a myopic view of this relationship. In particular, a limited number of relevant trustors (e.g., end-us
Externí odkaz:
http://arxiv.org/abs/2405.16310
Human-AI decision making is becoming increasingly ubiquitous, and explanations have been proposed to facilitate better Human-AI interactions. Recent research has investigated the positive impact of explanations on decision subjects' fairness percepti
Externí odkaz:
http://arxiv.org/abs/2305.00739
The creation of relevance assessments by human assessors (often nowadays crowdworkers) is a vital step when building IR test collections. Prior works have investigated assessor quality & behaviour, though into the impact of a document's presentation
Externí odkaz:
http://arxiv.org/abs/2304.10881
Public attention towards explainability of artificial intelligence (AI) systems has been rising in recent years to offer methodologies for human oversight. This has translated into the proliferation of research outputs, such as from Explainable AI, t
Externí odkaz:
http://arxiv.org/abs/2304.11218
Autor:
Tocchetti, Andrea, Corti, Lorenzo, Balayn, Agathe, Yurrita, Mireia, Lippmann, Philip, Brambilla, Marco, Yang, Jie
Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Robustness has been studied in many domains of AI, yet with different interpre
Externí odkaz:
http://arxiv.org/abs/2210.08906
Autor:
Farzin Beygui, Dorothée Balayn, Thierry Lobbedez, Marion Boulanger, Jean-Jacques Parienti, Maxence Ficheux, Laure Peyro-Saint-Paul, Blandine Lecrux, Manon Brossier, Antoine Morin, Antoine Lanot, Chloé Peron, Marie Brionne, C Béchade
Publikováno v:
BMJ Open, Vol 14, Iss 9 (2024)
Introduction Several randomised controlled trials have demonstrated that novel oral anticoagulants are safer compared with vitamin K antagonists for the management of non-valvular atrial fibrillation (NVAF) to prevent thromboembolic events in the gen
Externí odkaz:
https://doaj.org/article/eeabed87f335494691aa175502d1553f
In an effort to regulate Machine Learning-driven (ML) systems, current auditing processes mostly focus on detecting harmful algorithmic biases. While these strategies have proven to be impactful, some values outlined in documents dealing with ethics
Externí odkaz:
http://arxiv.org/abs/2205.04525
Researchers have identified datasets used for training computer vision (CV) models as an important source of hazardous outcomes, and continue to examine popular CV datasets to expose their harms. These works tend to treat datasets as objects, or focu
Externí odkaz:
http://arxiv.org/abs/2107.01824