AEQUITAS 2024
Fairness and Bias in AI

Table of Contents

• Summary: There were 35 papers submitted for peer-review to this workshop. Out of these, 17 papers were accepted for this volume, 17 as regular papers and 0 as short papers.

Papers

• Setting the AI Agenda – Evidence from Sweden in the ChatGPT Era
  Bastiaan Bruinsma, Annika Fredén, Kajsa Hansson, Moa Johansson, Pasko Kisić-Merino, Denitsa Saynova
• ProxiMix: Enhancing Fairness with Proximity Samples in Subgroups
  Jingyu Hu, Jun Hong, Mengnan Du, Weiru Liu
• Combining Fairness and Causal Graphs to Advance Both
  Lea Cohausz, Jakob Kappenberger, Heiner Stuckenschmidt
• Enhancing Algorithm Performance Understanding through tsMorph: Generating Semi-Synthetic Time Series for Robust Forecasting Evaluation
  Moisés Santos, André de Carvalho, Carlos Soares
• Leveraging Ontologies to Document Bias in Data
  Mayra Russo, Maria-Esther Vidal
• Measuring and Mitigating Bias for Tabular Datasets with Multiple Protected Attributes
  Manh Khoi Duong, Stefan Conrad
• Mitigating Toxicity in Dialogue Agents through Adversarial Reinforcement Learning
  Guillermo Villate-Castillo, Borja Sanz, Javier Del Ser
• Enforcing Fairness via Constraint Injection with FaUCI
  Matteo Magnini, Giovanni Ciatto, Roberta Calegari, Andrea Omicini
• Using Protected Attributes to Consider Fairness in Multi-Agent Systems
  Gabriele La Malfa, Jie M. Zhang, Michael Luck, Elizabeth Black
• Does spatio-temporal information benefit the video summarization task?
  Aashutosh Ganesh, Mirela Popa, Daan Odijk, Nava Tintarev
• Long-Term Fairness Strategies in Ranking with Continuous Sensitive Attributes
  Luca Giuliani, Eleonora Misino, Roberta Calegari, Michele Lombardi
• Data Quality Dimensions for Fair AI
  Camilla Quaresmini, Giuseppe Primiero
• Unmasking the Shadows: Leveraging Symbolic Knowledge Extraction to Discover Biases and Unfairness in Opaque Predictive Models
  Federico Sabbatini, Roberta Calegari
• Bias, Subjectivity and Norm in Large Language Models
  Thierry Poibeau
• From Inclusive Language to Inclusive AI: A Proof-of-Concept Study into Pre-Trained Models
  Marion Bartl, Susan Leavy
• FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and explainability
  Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz
• AI-fairness and equality of opportunity: a case study on educational achievement
  Angel S. Marrero, Gustavo A. Marrero, Carlos Bethencourt, Liam James, Roberta Calegari