Showing cs.CLShow all
3 papers · 1 filter
cs.CL2025
Steering Large Language Models for Machine Translation Personalization
Daniel Scalena, Gabriele Sarti, Arianna Bisazza +2
Large language models have simplified the production of personalized translations reflecting predefined stylistic constraints. However, these systems still struggle when stylistic…
cs.CL2024
A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering
Daniel Scalena, Elisabetta Fersini, Malvina Nissim
Adapting models to a language that was only partially present in the pre-training data requires fine-tuning, which is expensive in terms of both data and computational resources. A…
cs.CL2024
Multi-property Steering of Large Language Models with Dynamic Activation Composition
Daniel Scalena, Gabriele Sarti, Malvina Nissim
Activation steering methods were shown to be effective in conditioning language model generation by additively intervening over models' intermediate representations. However, the e…