Arjumand Younus

Qin Ruan, Jin Xu, Ruihai Dong et al.

Societal risk emanating from how recommender algorithms disseminate content online is now well documented. Emergent regulation aims to mitigate this risk through ethical audits and enabling new research on the social impact of algorithms. However, there is currently a need for tools and methods that enable such evaluation. This paper presents ARTAI, an evaluation environment that enables large-scale assessments of recommender algorithms to identify harmful patterns in how content is distributed online and enables the implementation of new regulatory requirements for increased transparency in recommender systems.

Delaram Golpayegani, Marta Lasek-Markey, Arjumand Younus et al.

The upsurge of policies and guidelines that aim to ensure Artificial Intelligence (AI) systems are safe and trustworthy has led to a fragmented landscape of AI governance. The European Union (EU) is a key actor in the development of such policies and guidelines. Its High-Level Expert Group (HLEG) issued an influential set of guidelines for trustworthy AI, followed in 2024 by the adoption of the EU AI Act. While the EU policies and guidelines are expected to be aligned, they may differ in their scope, areas of emphasis, degrees of normativity, and priorities in relation to AI. To gain a broad understanding of AI governance from the EU perspective, we leverage qualitative thematic analysis approaches to uncover prevalent themes in key EU documents, including the AI Act and the HLEG Ethics Guidelines. We further employ quantitative topic modelling approaches, specifically through the use of the BERTopic model, to enhance the results and increase the document sample to include EU AI policy documents published post-2018. We present a novel perspective on EU policies, tracking the evolution of its approach to addressing AI governance.

Arjumand Younus, Muhammad Atif Qureshi

Personalization despite being an effective solution to the problem information overload remains tricky on account of multiple dimensions to consider. Furthermore, the challenge of avoiding overdoing personalization involves estimation of a user's preferences in relation to different queries. This work is an attempt to make inferences about when personalization would be beneficial by relating observable user behavior to his/her social network usage patterns and user-generated content. User behavior on a search system is observed by means of team-draft interleaving whereby results from two retrieval functions are presented in an interleaved manner, and user clicks are utilised to infer preference for a certain retrieval function. This improves upon earlier work which had limited usefulness due to reliance on user survey results; our findings may aid real-time personalization in search systems by detecting a user-related and query-related personalization signals.