1 citations · 1 across the 5 of their papers we have counts for
6 papers
The Gold in Bias: Maturing the AI Design Process through Verification
Samira Maghool, Paolo Ceravolo
Bias in AI systems is typically framed as a flaw to be minimized, yet it also serves as a critical indicator of underlying weaknesses in data, modeling assumptions, and system desi…
Artificial Conversations, Real Results: Fostering Language Detection with Synthetic Data
Fatemeh Mohammadi, Tommaso Romano, Samira Maghool +1
Collecting high-quality training data is essential for fine-tuning Large Language Models (LLMs). However, acquiring such data is often costly and time-consuming, especially for non…
HH4AI: A methodological Framework for AI Human Rights impact assessment under the EUAI ACT
Paolo Ceravolo, Ernesto Damiani, Maria Elisa D'Amico +10
This paper introduces the HH4AI Methodology, a structured approach to assessing the impact of AI systems on human rights, focusing on compliance with the EU AI Act and addressing t…
Identifying Gender Stereotypes and Biases in Automated Translation from English to Italian using Similarity Networks
Fatemeh Mohammadi, Marta Annamaria Tamborini, Paolo Ceravolo +2
This paper is a collaborative effort between Linguistics, Law, and Computer Science to evaluate stereotypes and biases in automated translation systems. We advocate gender-neutral…
Enhancing Model Fairness and Accuracy with Similarity Networks: A Methodological Approach
Samira Maghool, Paolo Ceravolo
In this paper, we propose an innovative approach to thoroughly explore dataset features that introduce bias in downstream machine-learning tasks. Depending on the data format, we u…
Are Large Language Models the New Interface for Data Pipelines?
Sylvio Barbon Junior, Paolo Ceravolo, Sven Groppe +5
A Language Model is a term that encompasses various types of models designed to understand and generate human communication. Large Language Models (LLMs) have gained significant at…