Daniela Occhipinti

Researcher at @LanD_FBK, @FBK_research

website:

[Daniela Occhipinti @docchipinti8]

LLMs adjust their responses to their given persona and to their interlocutor’s…

…but what happens when they’re from different planets? 🧔🦸‍♂️
Find out in our #ACL2025NLP (main) paper!

👉Preprint: https://t.co/GV1pEEl6PP

[LanD @LanD_FBK]

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’.

Excited to share our #ACL2025NLP (main) paper by @docchipinti8 @m_guerini @MalvinaNissim

1/🧵

[Nicolò Penzo @penzo_nicolo]

🎶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 @m_guerini, @brulepri, @gg42554, @sara_hlt
🧵
https://t.co/WevpPnTYkz

[LanD @LanD_FBK]

Now at #LT2025FBK, @docchipinti8 is presenting our work on persona-based generation. 💪

[James Zou @james_y_zou]

We found a troubling emergent behavior in LLM.

💬When LLMs compete for social media likes, they start making things up
🗳️When they compete for votes, they turn inflammatory/populist

When optimized for audiences, LLMs inadvertently become misaligned—we call this Moloch’s Bargain

[CSHAM Tutorial (ACL2025) @csham_tutorial]

We're back from #ACL2025NLP and still buzzing from how well CSHAM went! Huge thanks to everyone who attended, asked questions, and made it such a great tutorial!

[LanD @LanD_FBK]

📢 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: https://t.co/9cQNmnLTsE
PhD Details: https://t.co/61OhXBrd6a

Deadline: August 22nd, 2025, hrs. 04:00 PM (CEST)

[Daniela Occhipinti @docchipinti8]

It was amazing meeting so many people this morning and chatting about how LLMs adapt not just to their given persona, but to the interlocutor’s too. I really enjoyed the poster session and loved everyone’s insights! 🚀

For more details: https://t.co/Cn6RpEg9TQ

#ACL2025NLP

[Daniela Occhipinti @docchipinti8]

@YisongMiao Thank you :)

[Daniela Occhipinti @docchipinti8]

Beyond happy for this result! 🥳🚀

[LanD @LanD_FBK]

🎉 The LanD group is excited to share that 3 of our papers made it into #ACL2025NLP!

Massive congrats to the authors: @docchipinti8, @russ_eau, @stefano_menini, @_FaribaSadeghi_, @ziorufus, @m_guerini, @MalvinaNissim.

More details and links to the papers coming soon! 👀

[Daniela Occhipinti @docchipinti8]

@lrzneedresearch Not yet, but it will be soon. We will post it as soon as it is out! :)

[CLiC-it Conference @CLiC_it_conf]

The #CLiCit2024 Best Student Paper Award goes to @russ_eau !! 🏆 @AILC_NLP #NLProc

[CLiC-it Conference @CLiC_it_conf]

Poster Session & Coffee Break #clicit2024 @AILC_NLP #NLProc

[LanD @LanD_FBK]

Today we will present three of our recent works at #CLiCit2024 with @helena_bonaldi, @docchipinti8, @russ_eau.
Don't miss the poster session today at 10 👀

[LanD @LanD_FBK]

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 @russ_eau , @oaraquei , and @m_guerini .

[LanD @LanD_FBK]

LanD(ed) in Pisa 🛬
#CLiCit2024 #NLProc

[Gian Maria Campedelli @CampedelliGian]

💭Remember the Stanford Prison Experiment?

📣“I Want to Break Free! Anti-Social Behavior and Persuasion Ability of LLMs in Multi-Agent Settings with Social Hierarchy”, our new pre-print, is out!

W/@penzo_nicolo, @itakello, @robdessi, @m_guerini, @brulepri, @stjaco

Check this🧵

[Helena Bonaldi @helena_bonaldi]

🚨 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 @grexit_ @NBenjaminOcampo @ECabrio @serena_villata @m_guerini

https://t.co/KaaYbCCbYw

A thread 🧵

[Nicolò Penzo @penzo_nicolo]

🍸Haven't you had enough rounds, Llama?

📣"Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations", our #EMNLP2024 paper!

With @mariamsajedinia, @brulepri, @sara_hlt, @m_guerini
🧵
https://t.co/WXsqIoCXGt

[Daniela Occhipinti @docchipinti8]

Dear Reviewer 2, these are NOT valid reasons to reject o poorly rate a paper! #ACL2024NLP

[Jerry Spanakis 🟥 🦋 gerasimoss.bsky.social @gerasimoss]

remember GloVe embeddings? of course you do, they are still being used (and we teach them for their simplicity and elegance), as @chrmanning pointed out in his speech. Congratulations on the 10yr Test-of-Time award! #ACL2024NLP