Projects

SALMON

Social Awareness for better Large Language Model Learning

TOLD

Thinking Out Loud - A Speech-Based Data Collection Framework

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.

The “r” in “woman” stands for rights. Auditing LLMs in Uncovering Social Dynamics in Implicit Misogyny

November, 2025
Persistent societal biases like misogyny express themselves more often implicitly than through openly hostile language.However, …

Generalizability of Media Frames: Corpus creation and analysis across countries

November, 2025
Frames capture aspects of an issue that are emphasized in a debate by interlocutors and can help us understand how political language …

No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models

November, 2025
Large language models (LLMs) are increasingly integrated into our daily lives and personalized. However, LLM personalization might also …

Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance

November, 2025
Expert persona prompting—assigning roles such as expert in math to language models—is widely used for task improvement. However, prior …

TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent

November, 2025
As large language models (LLMs) become integrated into sensitive workflows, concerns grow over their potential to leak confidential …