🚨 Our paper “Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering” has been accepted at #EMNLP2024! With Greta Damo Nicolás Benjamín Ocampo Elena Cabrio Serena Villata Marco Guerini arxiv.org/abs/2410.03466 A thread 🧵

🤔 What happens if a guard-LLM has to deal with a prisoner-LLM? 👀 Take a look at our new pre-print! arxiv.org/abs/2410.07109 💯 Great team, great work

Anti-Social Behavior and Persuasion Ability of LLMs This work studies the interaction patterns of LLMs in a multi-agent setting with social hierarchy. The study was done under a specific setting involving a guard and a prisoner who seeks additional yard time or escaping from

First talk from our group delivered by Nicolò Penzo at #EMNLP2024 👏👏👏 Next one will be on Thursday 10:45 in Brickell room, with Camilla Casula disclosing every you always wanted to know about synthetic data for hate speech detection #NLProc

Happy for presenting our work at #EMNLP2024 🥳 If you miss the talk, you can find the paper at the following link: aclanthology.org/2024.emnlp-mai… maryam sajedinia Bruno Lepri Sara Tonelli Marco Guerini

The full annotated data for this paper is also freely available on Github if you'd like to check it out! github.com/dhfbk/delving

Our group with colleagues (and friends!) at #EMNLP2024. Tomorrow there’s still the tutorial on hate speech countering!

🚨If you are attending #clicit2024 , go to discuss with Giovanni Valer about his work on Fassa Ladin! Add his poster session on your calendar 😉

To click it, or not to click it: that is the question. Our #CLiC-it2024 contribution is finally out: "To Click It or Not to Click It: An Italian Dataset for Neutralising Clickbait Headlines" authored by Daniel Russo , Óscar Araque , and Marco Guerini .

🚨 Today at #CS2Italy ! 🔗 Check it on arxiv: arxiv.org/abs/2410.07109