Marta Marchiori Manerba

hate speech detection (3) large language model (2) bias evaluation (2) bias mitigation (2) bias detection (2) fairness analysis (2) language model (2) fairness benchmark (1) human alignment (1) stereotype detection (1) model auditing (1) fairness benchmarking (1) disparate treatment (1) harmful belief (1) bert-based classifier (1) abusive language classification (1) active learning (1) sensitive demographic (1) transfer learning (1) text classification (1)