@land-fbk.bsky.social
47 followers 28 following 21 posts
Posts Media Videos Starter Packs
land-fbk.bsky.social
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 🙌
land-fbk.bsky.social
📢 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)
Reposted
csham-tutorial.bsky.social
The first invited speaker is Cathy Buerger from @dangerousspeech.org‬, with a talk titled "Co-designing Counterspeech: Rethinking AI’s Role". #ACL2025NLP
Reposted
csham-tutorial.bsky.social
What ethical questions arise when designing counterspeech? Gavin Abercrombie (@gavina.bsky.social) will guide us with a talk titled "Ethical considerations of counterspeech".
Reposted
csham-tutorial.bsky.social
What challenges unite counterspeech generation for hate speech and misinformation? Marco Guerini (@marcoguerini.bsky.social) will unpack this intersection.
Reposted
csham-tutorial.bsky.social
CSHAM continues with Daniel Russo (@daniel-russo.bsky.social) presenting on “NLP approaches to counterspeech for misinformation”
Reposted
csham-tutorial.bsky.social
CSHAM continues with Helena Bonaldi (@helenabon.bsky.social) sharing insights on "NLP approaches to counterspeech against hate".
Reposted
csham-tutorial.bsky.social
The tutorial starts with a presentation from Yi-Ling Chung on "Counterspeech in the real world: evidence from social science".
Reposted
csham-tutorial.bsky.social
CSHAM started 🔥
Join us in Hall N.1-N.2 at #ACL2025NLP
@marcoguerini.bsky.social
Reposted
csham-tutorial.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 👀
Reposted
csham-tutorial.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...
CSHAM
Sunday, July 27 - 14:00-17:30
sites.google.com
Reposted
csham-tutorial.bsky.social
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...
CSHAM - Program
Sunday, July 27 ‎(UTC+1)
sites.google.com
land-fbk.bsky.social
All together once again to greet @estrellavr15.bsky.social who is going back to Spain 💃🏼
Reposted
csham-tutorial.bsky.social
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...
CSHAM - Program
Sunday, July 27 ‎(UTC+1)
sites.google.com
land-fbk.bsky.social
7/🧵 🎯Fine-tuned models avoid this copy-paste behavior and reflect deeper persona traits, leading to more authentic persona-based dialogue.
land-fbk.bsky.social
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.
land-fbk.bsky.social
5/🧵 🎯 LLMs are able to generalize to “unfamiliar” topics (Harry speaking about kryptonite).
land-fbk.bsky.social
4/🧵 🎯 LLMs are not able to generalize to “unfamiliar” interlocutors (Harry speaking with Superman).
land-fbk.bsky.social
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…
land-fbk.bsky.social
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:
land-fbk.bsky.social
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/🧵
Reposted
aclmeeting.bsky.social
🗣️ 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...
Tutorials
ACL 2025 Conference Overview.
2025.aclweb.org