🇸🇬 Don’t miss @penzo-nicolo.bsky.social presenting his poster on synthetic Multi-Party Conversation generation at #AAAI26!
🏛️ Hall 2
🪧 Poster Board 257
⏰ Jan. 22, 12–2 PM
🎶One more “song”?
Come see our poster next week at #AAAI2026 on our paper:
📣 “Don’t Stop the Multi-Party! On Generating Synthetic Written Multi-Party Conversations with Constraints”
With @marcoguerini.bsky.social Bruno Lepri @gglavas.bsky.social @satonelli.bsky.social
🧵
arxiv.org/abs/2502.13592
Wrapping up #LT2025FBK with four contributions from our group: two oral presentations by Fariba Sadeghi and Daniela Occhipinti (@docchipinti8.bsky.social), and two posters by Helena Bonaldi (@helenabon.bsky.social) and Marco Guerini (@marcoguerini.bsky.social) 🚀
Exciting day at #INLG2025 in Hanoi! 🇻🇳
Daniel Russo (@daniel-russo.bsky.social ) and Stefano Menini presented "Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking"
🔗 tinyurl.com/3w8jykhd
🚀 Our annual, full-day Language Technologies showcase is back! Dive into the latest research highlights from FBK groups. Want in? We'd love to see you, but don't forget to register!
www.fbk.eu/en/event/346...
Back from #ACL2025NLP in Vienna 🇦🇹! We presented three posters, organized a tutorial, and had tons of amazing interactions. Huge thanks to our amazing team and collaborators for all the hard work 🙌
📢 Do you want to join our group? We opened **two** calls for a fully funded PhD. Details are in the image and at the following links.
Calls: iecs.unitn.it/education/ad...
PhD Details: iecs.unitn.it/education/ad...
Deadline: August 22nd, 2025, hrs. 04:00 PM (CEST)
The first invited speaker is Cathy Buerger from @dangerousspeech.org, with a talk titled "Co-designing Counterspeech: Rethinking AI’s Role". #ACL2025NLP
What ethical questions arise when designing counterspeech? Gavin Abercrombie (@gavina.bsky.social) will guide us with a talk titled "Ethical considerations of counterspeech".
What challenges unite counterspeech generation for hate speech and misinformation? Marco Guerini (@marcoguerini.bsky.social) will unpack this intersection.
CSHAM continues with Daniel Russo (@daniel-russo.bsky.social) presenting on “NLP approaches to counterspeech for misinformation”
CSHAM continues with Helena Bonaldi (@helenabon.bsky.social) sharing insights on "NLP approaches to counterspeech against hate".
The tutorial starts with a presentation from Yi-Ling Chung on "Counterspeech in the real world: evidence from social science".
CSHAM started 🔥
Join us in Hall N.1-N.2 at #ACL2025NLP
@marcoguerini.bsky.social
Last but not least, we present the CSHAM organisers. Daniel Russo (@daniel-russo.bsky.social), Helena Bonaldi (@helenabon.bsky.social), Yi-Ling Chung, Gavin Abercrombie (@gavina.bsky.social), Marco Guerini (@marcoguerini.bsky.social).
We are excited to see you all tomorrow at 2 pm at #ACL2025NLP 👀
LanD(ing) in Vienna for #ACL2025NLP 🚀
@daniel-russo.bsky.social @helenabon.bsky.social
@docchipinti8.bsky.social
@marcoguerini.bsky.social
LanD(ing) in Vienna for #ACL2025NLP 🚀
@daniel-russo.bsky.social @helenabon.bsky.social
@docchipinti8.bsky.social
@marcoguerini.bsky.social
📣 Planning to attend #ACL2025NLP? Then don’t miss the "NLP for Counterspeech against Hate and Misinformation" tutorial!
🗓️ Sunday, July 27, 2025
🕑 14:00 - 17:30
📍 ACL2025, Austria Center Vienna
Details on our website ⤵️ sites.google.com/view/nlp4csh...
Delighted to introduce Cathy Buerger, our first invited speaker for the "NLP for Counterspeech against Hate and Misinformation" tutorial. Join us to hear her insightful work on "Co-designing Counterspeech: Rethinking AI's Role" #ACL2025NLP
More details ⤵️
sites.google.com/view/nlp4csh...
All together once again to greet @estrellavr15.bsky.social who is going back to Spain 💃🏼
Simone Fontana (@simofons.bsky.social), Editorial Director at @facta.news, is our second invited speaker! His talk, "Countering Disinformation and Hate Speech: The Role of Journalism", will offer insights from a practitioner’s perspective! #ACL2025NLP
Details ⤵️
sites.google.com/view/nlp4csh...
8/🧵 For more details, you can find the preprint here 👉 arxiv.org/abs/2505.24613
7/🧵 🎯Fine-tuned models avoid this copy-paste behavior and reflect deeper persona traits, leading to more authentic persona-based dialogue.
6/🧵🎯 Zero-shot models (seem to) perform much better than fine-tuned ones, but only because they copy biographical details from the prompt, making speaker identification trivial and conversations shallow.
5/🧵 🎯 LLMs are able to generalize to “unfamiliar” topics (Harry speaking about kryptonite).
4/🧵 🎯 LLMs are not able to generalize to “unfamiliar” interlocutors (Harry speaking with Superman).
3/🧵 🎯 Speaker personas are easier to recognize when we know the interlocutor’s bio. Thus LLMs don’t just follow their own persona, but adapt to their conversation partner. Still…
2/🧵 We cast the problem as a speaker recognition task: given a dialogue, guess the biography of the target speaker. Is it easier to guess if we also know the interlocutor’s biography? Is it easier if both know each other?
🧐 Following our key findings:
What happens when Harry meets Superman instead of Sally for a chat? 🧔🦸♂️
We explore how LLMs adapt their responses not just to their given persona, but also to their interlocutors’.
📣 New #ACL2025NLP (main) paper by @docchipinti8.bsky.social @marcoguerini.bsky.social @malvinanissim.bsky.social
1/🧵
🗣️ Discover "NLP for Counterspeech against Hate and Misinformation" at #ACL2025NLP! This tutorial bridges CS, social sciences & policy, exploring among others the role of LLMs. #HateSpeech #Misinformation #NLProc #ResponsibleAI
👉 2025.aclweb.org/program/tuto...
