Daniel Scalena

According to our database, Daniel Scalena authored at least 6 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Steering Large Language Models for Machine Translation Personalization.

Daniel Scalena, Gabriele Sarti, Arianna Bisazza, Elisabetta Fersini, Malvina Nissim

CoRR, May, 2025

2024

Multi-property Steering of Large Language Models with Dynamic Activation Composition.

Daniel Scalena, Gabriele Sarti, Malvina Nissim

CoRR, 2024

A Gentle Push Funziona Benissimo: Making Instructed Models in Italian via Contrastive Activation Steering.

Daniel Scalena, Elisabetta Fersini, Malvina Nissim

Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024), 2024

CALAMITA: Challenge the Abilities of LAnguage Models in ITAlian.

Giuseppe Attanasio, Pierpaolo Basile, Federico Borazio, Danilo Croce, Maria Francis, Jacopo Gili, Elio Musacchio, Malvina Nissim, Viviana Patti, Matteo Rinaldi, Daniel Scalena

Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024), 2024

2023

Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence.

Daniel Scalena, Gabriele Sarti, Malvina Nissim, Elisabetta Fersini

CoRR, 2023

MIND at SemEval-2023 Task 11: From Uncertain Predictions to Subjective Disagreement.

Giulia Rizzi, Alessandro Astorino, Daniel Scalena, Paolo Rosso, Elisabetta Fersini

Proceedings of the The 17th International Workshop on Semantic Evaluation, 2023