International Scientific Report on the Safety of Advanced AI (Interim Report)

Y Bengio, S Mindermann, D Privitera… - ar** Review.
G Wolbring, L Nasir - Societies (2075-4698), 2024 - search.ebscohost.com
Disabled people face many social problems in their lives, as outlined by the UN Convention
on the Rights of Persons with Disabilities. These problems often increase when disabled …

VA+ Embeddings STAR: A State‐of‐the‐Art Report on the Use of Embeddings in Visual Analytics

Z Huang, D Witschard, K Kucher… - Computer Graphics …, 2023 - Wiley Online Library
Over the past years, an increasing number of publications in information visualization,
especially within the field of visual analytics, have mentioned the term “embedding” when …

VERB: Visualizing and interpreting bias mitigation techniques geometrically for word representations

A Rathore, S Dev, JM Phillips, V Srikumar… - ACM Transactions on …, 2024 - dl.acm.org
Word vector embeddings have been shown to contain and amplify biases in the data they
are extracted from. Consequently, many techniques have been proposed to identify …

DramatVis Personae: Visual text analytics for identifying social biases in creative writing

MN Hoque, B Ghai, N Elmqvist - … of the 2022 ACM Designing Interactive …, 2022 - dl.acm.org
Implicit biases and stereotypes are often pervasive in different forms of creative writing such
as novels, screenplays, and children's books. To understand the kind of biases writers are …

Ethical assessments and mitigation strategies for biases in AI-systems used during the COVID-19 pandemic

A De Manuel, J Delgado, I Parra Jounou… - Big Data & …, 2023 - journals.sagepub.com
The main aim of this article is to reflect on the impact of biases related to artificial intelligence
(AI) systems developed to tackle issues arising from the COVID-19 pandemic, with special …

An empirical study on the fairness of pre-trained word embeddings

E Sesari, M Hort, F Sarro - Proceedings of the 4th Workshop on …, 2022 - aclanthology.org
Pre-trained word embedding models are easily distributed and applied, as they alleviate
users from the effort to train models themselves. With widely distributed models, it is …