Deep Learning

This dissertation bridges the gap between scientific insights into how language models work and practical benefits for users of these systems, paving the way for better human-AI interaction practices for professional translators and everyday users worldwide.

We evaluate prompting and steering based methods for machine translation personalization in the literary domain.

We propose Dynamic Activation Composition, an adaptive approach for multi-property activation steering of LLMs

MIRAGE uses model internals for faithful answer attribution in retrieval-augmented generation applications.

IT5s are the first encoder-decoder transformers pretrained on more than 40 billion Italian words.

This primer provides a concise technical introduction to the current techniques used to interpret the inner workings of Transformer-based language models, focusing on the generative decoder-only architecture.

We propose DecoderLens, a method to interpret the iterative refinement of representations in encoder-decoder Transformer models.

We introduce PECoRe, an interpretability framework for identifying context dependence in language model generations.

We introduce Retrieval and Attribute-Marking enhanced Prompting (RAMP) to perform attribute-controlled MT with multilingual LLMs.

We analyze input contributions of char-level MT models and show how they modulate word and character-level information.