74 citations · 389 across the 26 of their papers we have counts for
7 papers · 1 filter
NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers
Salvatore Greco, Ke Zhou, Licia Capra +2
AI regulations are expected to prohibit machine learning models from using sensitive attributes during training. However, the latest Natural Language Processing (NLP) classifiers,…
WEIRD ICWSM: How Western, Educated, Industrialized, Rich, and Democratic is Social Computing Research?
Ali Akbar Septiandri, Marios Constantinides, Daniele Quercia
Much of the research in social computing analyzes data from social media platforms, which may inherently carry biases. An overlooked source of such bias is the over-representation…
Using Self-supervised Learning Can Improve Model Fairness
Sofia Yfantidou, Dimitris Spathis, Marios Constantinides +3
Self-supervised learning (SSL) has become the de facto training paradigm of large models, where pre-training is followed by supervised fine-tuning using domain-specific data and la…
Implications of Regulations on the Use of AI and Generative AI for Human-Centered Responsible Artificial Intelligence
Marios Constantinides, Mohammad Tahaei, Daniele Quercia +13
With the upcoming AI regulations (e.g., EU AI Act) and rapid advancements in generative AI, new challenges emerge in the area of Human-Centered Responsible Artificial Intelligence…
Guidelines for Integrating Value Sensitive Design in Responsible AI Toolkits
Malak Sadek, Marios Constantinides, Daniele Quercia +1
Value Sensitive Design (VSD) is a framework for integrating human values throughout the technology design process. In parallel, Responsible AI (RAI) advocates for the development o…
User Characteristics in Explainable AI: The Rabbit Hole of Personalization?
Robert Nimmo, Marios Constantinides, Ke Zhou +2
As Artificial Intelligence (AI) becomes ubiquitous, the need for Explainable AI (XAI) has become critical for transparency and trust among users. A significant challenge in XAI is…