SCALENA DANIEL

Magazzù, G., Sormani, A., Rizzi, G., Pulerà, F., Scalena, D., Cariddi, S., et al. (2025). BeaverTails-IT: Towards a Safety Benchmark for Evaluating Italian Large Language Models. In Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025) (pp.625-635). CEUR Workshop Proceedings. Dettaglio

Rizzi, G., Magazzù, G., Sormani, A., Pulerà, F., Scalena, D., Fersini, E. (2025). Uncovering Unsafety Traits in Italian Language Models. In Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025) (pp.974-982). CEUR Workshop Proceedings. Dettaglio

Scalena, D., Sarti, G., Nissim, M. (2024). Multi-property Steering of Large Language Models with Dynamic Activation Composition. In BlackboxNLP 2024 - 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP - Proceedings of the Workshop (pp.577-603). Association for Computational Linguistics (ACL) [10.18653/v1/2024.blackboxnlp-1.34]. Dettaglio

Rizzi, G., Astorino, A., Scalena, D., Rosso, P., Fersini, E. (2023). MIND at SemEval-2023 Task 11: From Uncertain Predictions to Subjective Disagreement. In 17th International Workshop on Semantic Evaluation, SemEval 2023 - Proceedings of the Workshop (pp.556-564). Association for Computational Linguistics. Dettaglio