profile picture

Marco Guerini

hate speech countering

dialogue generation

natural language generation

knowledge-grounded generation

automatic text summarization

counter narrative generation

human-machine collaboration

stance detection

reasoning

hate speech

pre-trained language models

text classification

survey

human-in-the-loop

sentiment analysis

15

presentations

SHORT BIO

Marco Guerini is a researcher in Computational Linguistics and head of the Language and Dialogue Technologies group at Fondazione Bruno Kessler. He works on persuasive communication, sentiment analysis and social media. In recent years he focused on the development of AI technologies to counter online hate speech and misinformation. He graduated in Philosophy and received his Ph.D. in Information and Communication Technologies in 2006 from the University of Trento. He is author of several scientific publications, published in top-level conference proceedings and international journals.

Presentations

Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering

Helena Bonaldi and 5 other authors

Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations

Nicolò Penzo and 4 other authors

Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models

Daniela Occhipinti and 6 other authors

NLP for Counterspeech against Hate: A Survey and How-To Guide

Helena Bonaldi and 3 other authors

PRODIGy: a PROfile-based DIalogue Generation dataset

Daniela Occhipinti and 2 other authors

Putting Context in Context: the Impact of Discussion Structure on Text Classification

Nicolò Penzo and 4 other authors

Benchmarking the Generation of Fact Checking Explanations | VIDEO

Daniel Russo and 2 other authors

Countering Misinformation via Emotional Response Generation

Daniel Russo and 3 other authors

Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering

Helena Bonaldi and 3 other authors

Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement

Elisa Leonardelli and 4 other authors

Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement

Elisa Leonardelli and 4 other authors

Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech

Yi-Ling Chung and 2 other authors

Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech

Marco Guerini and 3 other authors

Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech

Yi-Ling Chung and 2 other authors

Regrexit or not Regrexit: Aspect-based Sentiment Analysis in Polarized Contexts

Vorakit Vorakitphan and 3 other authors

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Presentations
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2025 Underline - All rights reserved