1 citations · 1 across the 5 of their papers we have counts for
6 papers
The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers
Samuele Vallisa, Federico Ravenda, Claudio Palominos +5
Transformer representations describe trajectories through high-dimensional vector spaces, which are shaped dynamically as tokens incorporate relational context across layers. Such…
A general framework for adaptive nonparametric dimensionality reduction
Antonio Di Noia, Federico Ravenda, Antonietta Mira
Dimensionality reduction is a fundamental task in modern data science. Several projection methods specifically tailored to take into account the non-linearity of the data via local…
Navigating through the hidden embedding space: steering LLMs to improve mental health assessment
Federico Ravenda, Seyed Ali Bahrainian, Andrea Raballo +1
The rapid evolution of Large Language Models (LLMs) is transforming AI, opening new opportunities in sensitive and high-impact areas such as Mental Health (MH). Yet, despite these…
Zero-Shot and Efficient Clarification Need Prediction in Conversational Search
Lili Lu, Chuan Meng, Federico Ravenda +2
Clarification need prediction (CNP) is a key task in conversational search, aiming to predict whether to ask a clarifying question or give an answer to the current user query. Howe…
Are LLMs effective psychological assessors? Leveraging adaptive RAG for interpretable mental health screening through psychometric practice
Federico Ravenda, Seyed Ali Bahrainian, Andrea Raballo +2
In psychological practices, standardized questionnaires serve as essential tools for assessing mental health through structured, clinically-validated questions (i.e., items). While…
The Emotional Spectrum of LLMs: Leveraging Empathy and Emotion-Based Markers for Mental Health Support
Alessandro De Grandi, Federico Ravenda, Andrea Raballo +1
The increasing demand for mental health services has highlighted the need for innovative solutions, particularly in the realm of psychological conversational AI, where the availabi…