activity
20242026
collaborators

10 papers

cs.CL2026

RooseBERT: A New Deal For Political Language Modelling

Deborah Dore, Elena Cabrio, Serena Villata

The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse such content with the f…

cs.CL2026

Compact Prompting in Instruction-tuned LLMs for Joint Argumentative Component Detection

Sofiane Elguendouze, Erwan Hain, Elena Cabrio +1

Argumentative component detection (ACD) is a core subtask of Argument(ation) Mining (AM) and one of its most challenging aspects, as it requires jointly delimiting argumentative sp…

cs.CL2026

PEACE 2.0: Grounded Explanations and Counter-Speech for Combating Hate Expressions

Greta Damo, Stéphane Petiot, Elena Cabrio +1

The increasing volume of hate speech on online platforms poses significant societal challenges. While the Natural Language Processing community has developed effective methods to a…

cs.LG2025

Merging Embedded Topics with Optimal Transport for Online Topic Modeling on Data Streams

Federica Granese, Benjamin Navet, Serena Villata +1

Topic modeling is a key component in unsupervised learning, employed to identify topics within a corpus of textual data. The rapid growth of social media generates an ever-growing…

cs.LG2025

Stick-Breaking Embedded Topic Model with Continuous Optimal Transport for Online Analysis of Document Streams

Federica Granese, Serena Villata, Charles Bouveyron

Online topic models are unsupervised algorithms to identify latent topics in data streams that continuously evolve over time. Although these methods naturally align with real-world…

cs.CL2025

Beating Harmful Stereotypes Through Facts: RAG-based Counter-speech Generation

Greta Damo, Elena Cabrio, Serena Villata

Counter-speech generation is at the core of many expert activities, such as fact-checking and hate speech, to counter harmful content. Yet, existing work treats counter-speech gene…