👋 About Me
I am a PhD candidate in Computer Science at Università della Svizzera italiana (USI) in Lugano, Switzerland, specializing in Natural Language Processing for Digital Health. I hold a Master’s degree in Statistics from Università Milano-Bicocca, with expertise in probabilistic modeling and machine learning.
My research explores advanced NLP methods, with applications spanning mental health, Conversational AI, and Information Retrieval. Beyond NLP, I apply probabilistic deep learning techniques to time series analysis and engage in general machine learning research.
🧑💻 Research Interests
Understanding minds through language
Tailoring AI systems for automated screening and assessment of mental health conditions using digital data sources, including social media text and conversational interactions. My work applies psychological frameworks to design clinically relevant NLP systems that can identify behavioral patterns indicative of mental health disorders.
- mental health screening
- social media text
- conversational data
- psychological frameworks
Trust, but verify
Recently exploring interpretability methods and uncertainty quantification techniques to enhance the reliability and trustworthiness of large language models, with applications to clinical NLP.
- interpretability
- uncertainty quantification
- clinical NLP
Finding the needle in the haystack
Researching retrieval methods and ranking algorithms to improve access to relevant information in specialized domains. The aim is to develop effective search systems and explore retrieval-augmented generation techniques for knowledge-intensive applications.
- information retrieval
- retrieval-augmented generation
Good things come in small packages
Investigating methods to improve the performance of small language models on clinically relevant diagnostic and assessment tasks. My research focuses on adapting and optimizing compact models through knowledge distillation, supervised fine-tuning, and reinforcement learning, with the goal of developing efficient models that can approach the diagnostic capabilities of larger systems while requiring substantially fewer computational resources.
- knowledge distillation
- supervised fine-tuning
- reinforcement learning
I’ve created a repository that I regularly update with available datasets from the literature for NLP research in Mental Health, intended for all practitioners. If you’re interested, check out the following link: [link].
If you’d like to discuss any NLP-related topics, feel free to contact me at:
federico.ravenda [at] usi.ch
Publications
✰ denotes equal contributions
The Changing Geometry of Grammar: Dimensionality and Neighborhood Reorganization across Transformer Layers
Vallisa, S.✰, Ravenda, Federico✰, Palominos C., He R., Raballo A., Mira A., Homan P., Hinzen W.
[paper] Submitted to *August 2026 ARR *TONY: an open-source TOolkit for Nlp in psYchology
Ravenda, Federico, Ravenda, Sofia Irene, Karpenko V., Montagnani, D., Mira, A., Raballo, A.
[paper] [Big News! 🤩] Accepted as Main Paper at Demo ACL 2026PersonalityDBench: A Dataset for Personality Disorders - from Modeling to Controlled Generation
Ravenda, Federico, Bahrainian, S. A., Montagnani, D., Mira, A., Raballo, A.
[paper] [Big News! 🤩] Accepted as Main Conference Paper at ACL 2026A general framework for adaptive nonparametric dimensionality reduction
Di Noia, A.✰, Ravenda, Federico✰, and Antonietta Mira.
[paper] Accepted at Nature Scientific Reports
Nature Scientific Reports (2026).Rethinking psychometrics through LLMs: how item semantics shape measurement and prediction in psychological questionnaires.
Ravenda, Federico, Preti, A., Poletti, M., Mira, A., & Raballo, A.
[paper] Nature Scientific Reports, 15(1), 37313, (2025).Navigating through the hidden embedding space: steering LLMs to improve mental health assessment
Ravenda, Federico, Bahrainian, S. A., Raballo, A., & Mira, A.
[paper] Accepted at SAC’2026Are llms effective psychological assessors? leveraging adaptive rag for interpretable mental health screening through psychometric practice
Ravenda, Federico, Bahrainian, S.A., Raballo, A., Mira, A., & Kando, N.
[paper] [Big News! 🤩] Accepted as Main Conference Paper at ACL 2025Diagnosing schizophrenia spectrum disorders: Large language models (LLMs) vs. leading international psychiatrists (LIPs)
Raballo, A., Ravenda, Federico, & Mira, A.
[paper] Psychiatry and Clinical Neurosciences, 79(9), 599.From Evidence Mining to Meta-Prediction: a Gradient of Methodologies for Task-Specific Challenges in Psychological Assessment
Ravenda, Federico, Kara-Isitt, F. Z., Swift, S., Mira, A., & Raballo, A.
[paper] Computational Linguistics and Clinical Psychology (CLPsych 2025)The emotional spectrum of llms: Leveraging empathy and emotion-based markers for mental health support
De Grandi, A.✰, Ravenda, Federico✰, Raballo, A., & Crestani, F.
[paper] Computational Linguistics and Clinical Psychology (CLPsych 2025)Tailoring adaptive-zero-shot retrieval and probabilistic modelling for psychometric data\ Ravenda, Federico, Bahrainian, S.A., Kando, N., Mira, A., Raballo, A., & Crestani, F.
[paper] The 40th ACM/SIGAPP Symposium on Applied Computing (SAC ‘25), 2025Transforming social media text into predictive tools for depression through AI: A test-case study on the Beck Depression Inventory-II.
Ravenda, Federico, Preti, A., Poletti, M., Mira, A., Crestani, F., & Raballo, A.
[paper] PLOS Digital Health, 4(6), e0000848.Zero-shot and efficient clarification need prediction
Lu, L., Meng, C., Ravenda, Federico, Aliannejadi, M., & Crestani, F.
[paper] European Conference of Information Retrieval, ECIR 2025, 2025A self-supervised seed-driven approach to topic modelling and clustering
Ravenda, Federico, Bahrainian, S.A., Raballo, A., Mira, A., & Crestani, F.
[paper] Journal of Intelligent Information Systems, pages 1-21, 2024A probabilistic spatio-temporal neural network to forecast covid-19 counts
Ravenda, Federico, Cesarini, M., Peluso, S., & Mira, A.
[paper] International Journal of Data Science and Analytics, pages 1-8, 2024Opinionated texts in social media: A proposal for evaluative judgement methodology\
Bączkowska, A., Negrea-Busuioc, E., Guzek, D., Liebeskind, C., Hess, A., Crestani, F., Ravenda, Federico, et al.
[paper] Beyond Philology An International Journal of Linguistics, Literary Studies and English Language Teaching, pages 203-280, 2024Spatio-temporal distribution, prediction and relationship of three major acute cardiovascular events: Out-of-hospital cardiac arrest, st-elevation myocardial infarction and stroke
Auricchio, A., Scquizzato, T., Ravenda, Federico, Cresta, R., Peluso, S., Caputo, M.L., Tonazzi, S., Benvenuti, C., & Mira, A.
[paper] Resuscitation Plus, volume 20, page 100810, 2024