SCALENA DANIEL

Scalena, D., Zotos, L., Fersini, E., Nissim, M., Ustun, A. (In corso di stampa). EAGER: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling. Intervento presentato a: Forty-third International Conference on Machine Learning (ICML 2026), Seul, Korea. Dettaglio

Nissim, M., Croce, D., Patti, V., Basile, P., Attanasio, G., Musacchio, E., et al. (2026). Challenging the Abilities of Large Language Models in Italian: a Community Initiative. IJCOL, 12(1), 31-109 [10.17454/ijcol121.02]. 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

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

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