3 papers
cs.CL2025
Ideology-Based LLMs for Content Moderation
Stefano Civelli, Pietro Bernardelle, Nardiena A. Pratama +1
Large language models (LLMs) are increasingly used in content moderation systems, where ensuring fairness and neutrality is essential. In this study, we examine how persona adoptio…
cs.CV2025
Perception of Visual Content: Differences Between Humans and Foundation Models
Nardiena A. Pratama, Shaoyang Fan, Gianluca Demartini
Human-annotated content is often used to train machine learning (ML) models. However, recently, language and multi-modal foundational models have been used to replace and scale-up…
cs.CL2025
Are Large Language Models Good Data Preprocessors?
Elyas Meguellati, Nardiena Pratama, Shazia Sadiq +1
High-quality textual training data is essential for the success of multimodal data processing tasks, yet outputs from image captioning models like BLIP and GIT often contain errors…