Get started
Author

Daniel Scalena

Observed names: Scalena D., Scalena, D, Scalena, Daniel, Scalena, Daniel; id_orcid 0009-0006-0518-6504
ORCID: 0009-0006-0518-6504
Observed ORCID: 0009-0006-0518-6504
OpenAlex ID: A5092596181
Multi-property Steering of Large Language Models with Dynamic Activation Composition
2024 · Daniel Scalena, Gabriele Sarti, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · 4
PDF
MIND at SemEval-2023 Task 11: From Uncertain Predictions to Subjective Disagreement
2023 · Giulia Rizzi, Alessandro Astorino, et al. · International Workshop on Semantic Evaluation (SemEval) · 2
PDF
Steering Large Language Models for Machine Translation Personalization
2026 · Daniel Scalena, Gabriele Sarti, et al. · Conference of the European Chapter of the Association for Computational Linguistics · 1
PDF
"Don't Say It!": Constraints, Compliance, and Communication when Language Models Play Taboo
2026 · Candussio, Sara, Padovani, Francesca, et al. · arXiv (Cornell University)
PDF
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
2026 · Scalena, Daniel, Candussio, Sara, et al. · arXiv (Cornell University)
PDF
Steering Large Language Models for Machine Translation Personalization
2026 · Association for Computational Linguistics 2026, Bisazza, Arianna, et al. · Underline Science Inc.
Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models
2026 · Sara Candussio, Daniel Scalena, et al. · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)
PDF
Gender Violence in Numbers:Prompting Italian LLMs to Characterize Crimes Against Women
2025 · Rizzi, Giulia, Scalena, Daniel; id_orcid 0009-0006-0518-6504, et al. · University of Groningen research database (University of Groningen / Centre for Information Technology)
Uncovering Unsafety Traits in Italian Language Models
2025 · Rizzi, G, Magazzù, G, et al. · BOA (University of Milano-Bicocca)
PDF
A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering
2024 · Scalena, Daniel, Fersini, Elisabetta, et al. · arXiv (Cornell University)
PDF
CALAMITA: Challenge the Abilities of LAnguage Models in ITAlian
2024 · Attanasio G., Basile P., et al. · Institutional Research Information System University of Turin (University of Turin)
PDF
Let the Models Respond: Interpreting Language Model Detoxification Through the Lens of Prompt Dependence
2023 · Scalena, Daniel, Sarti, Gabriele, et al. · arXiv (Cornell University)
PDF
Works count: 17
Citation count: 7
H-index: 2
I10-index:
Year
Topic
Type