MilaNLP Lab

We are the Milan Natural Language Processing Group. We study, develop and deploy NLP algorithms to solve real-world problems.

Previous Next

Meet the team!

Researchers

Avatar

Dirk Hovy

Full Professor

Avatar

Debora Nozza

Assistant Professor

Avatar

Albert Wendsjö

Visiting Researcher

Avatar

Arianna Muti

Postdoc

Avatar

Donya Rooein

Postdoc

Avatar

Elisa Bassignana

Visiting Postdoc

Avatar

Emanuele Moscato

Postdoc

Avatar

Joachim Baumann

Postdoc

Avatar

Paul Röttger

Postdoc

Avatar

Tanise Ceron

Postdoc

Projects

INDOMITA

Innovative Demographically-aware Hate Speech Detection in Online Media in Italian

PERSONAE

Personalized and Subjective approaches to Natural Language Processing

MENTALISM

Measuring, Tracking, and Analyzing Inequality using Social Media

INTEGRATOR

Incorporating Demographic Factors into Natural Language Processing Models

Twitter Healthy Conversations

Devising Metrics for Assessing Echo Chambers, Incivility, and Intolerance on Twitter

Recent BlueSky activity

Recent Publications

Quickly discover relevant content by filtering publications.

Beyond Prompt Brittleness: Evaluating the Reliability and Consistency of Political Worldviews in LLMs

March, 2025
Due to the widespread use of large language models (LLMs), we need to understand whether they embed a specific “worldview” and what …
PDF Project

Toeing the Party Line: Election Manifestos as a Key to Understand Political Discourse on Twitter

March, 2025
Political discourse on Twitter is a moving target: politicians continuously make statements about their positions. It is therefore …
PDF Project

MilaNLP@Multilingual Counterspeech Generation: Evaluating Translation and Background Knowledge Filtering

March, 2025
We describe our participation in the Multilingual Counterspeech Generation shared task, which aims to generate a counternarrative to …
PDF Project

MONICA: Monitoring Coverage and Attitudes of Italian Measures in Response to COVID-19

March, 2025
Modern social media have long been observed as a mirror for public discourse and opinions. Especially in the face of exceptional …
PDF

The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models

December, 2024
Human feedback is central to the alignment of Large Language Models (LLMs). However, open questions remain about methods (how), domains …
PDF Project
See all publications