Elisa Bassignana

📣 New Preprint!
Have you ever wondered what the political content in LLM's training data is? What are the political opinions expressed? What is the proportion of left- vs right-leaning documents in the pre- and post-training data? Do they correlate with the political biases reflected in models?

Next year #clicit2026 will be in……Palermo!

MilaNLPers at CLiC-it 2025 presenting "Probing Feminist Representations: A Study of Bias in LLMs and Word Embeddings"

Check the paper at clic2025.unica.it/wp-content/u...

#NLProc #clicit25

Big congrats to our postdoc @elisabassignana.bsky.social for the well deserved Social Impact award at #ACL2025NLP!!

The Best Social Impact Papers 🏆 #ACL2025NLP

Huge congratulations again to all the outstanding and best paper award winners at #ACL2025NLP! 🏆 Your innovative research is pushing the boundaries of computational linguistics. 🤯 We are increadibly proud of all this wonderful work!
#ACL2025NLP #OutstandingPapers #Awards

Super proud to receive the Social Impact award at #ACL2025NLP for our paper together with @amandacurry.bsky.social (eq contribution) and @dirkhovy.bsky.social 🎉

#NLProc

We’re incredibly proud to announce that our lab received two #ACL2025 awards: Best Social Impact Paper for @elisabassignana.bsky.social and @dirkhovy.bsky.social , and Outstanding Paper for @paul-rottger.bsky.social.

Congratulations to them and to all collaborators who made this possible!

Having a great time at #ACL2025NLP!

#NLProc

@milanlp.bsky.social @ #ACL2025 in #Vienna!

#NLProc

Next week I'll be at #ACL2024NLP to present our work about the interplay between SES and LLM usage 🇦🇹
I will present it on Wednesday morning and also take part in a panel at the end of the session.

🤗: shorturl.at/W77Kq

If you're interested in the topic, feel free to reach out for a chat!

#NLProc

📣 Next week we will be in Vienna for @aclmeeting.bsky.social to present a couple of works from our lab!

Find more about each of them below 🧵👇

#NLP #NLProc #ACL2025NLP @itu.dk @aicentre.dk

🎉 The @milanlp.bsky.social lab is excited to present 15 papers and 1 tutorial at #ACL2025 & workshops! Grateful to all our amazing collaborators, see everyone in Vienna! 🚀

Last week we held our 1st MilaNLP retreat by beautiful Lago Maggiore! ⛰️🌊
We shared research ideas, stories (academic & beyond), and amazing food. It was a great time to connect outside of the usual lab working days, and most importantly, strengthen our bonds as a team. #ResearchLife #NLProc

Stiamo vivendo una rivoluzione tecnologica, ma quanto conosciamo realmente l'uso dell'IA nella nostra quotidianità? Aiuta a scoprirlo compilando questo breve questionario (10 min): bit.ly/sondaggio_ai...

🔍 Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio!

👉 bit.ly/sondaggio_ai...

(è anonimo, richiede ~10 minuti, e se partecipi o lo fai girare ci aiuti un sacco🙏)

Ci interessa anche raggiungere persone che non si occupano e non sono esperte di AI!

📢 New #ACL2025 preprint by our postdoc @elisabassignana.bsky.social about the impact of socioeconomic status (SES) on the adoption and usage of language technologies!

A first step for better understanding the AI Gap across SES and develop more inclusive language technologies ⚖️🤖

#NLProc @itu.dk

📢 The Copenhagen NLP Symposium on June 20th!

- Invited talks by @loubnabnl.hf.co (HF) @mziizm.bsky.social (Cohere) @najoung.bsky.social (BU) @kylelo.bsky.social (AI2) Yohei Oseki (UTokyo)
- Exciting posters by other participants

Register to attend and/or present your poster at cphnlp.github.io /1

Check out the full paper here:
🔗 lnkd.in/dtsH3gaX
🤗 lnkd.in/d7diuBJh

#ACL2025 #ACL #NLProc #NLP #AI #DigitalDivide #LLM #AIethics #sociotechnical

We argue for designing NLP systems that actively account for socioeconomic linguistic variation.
Bridging the AI gap means more than just making tools accessible—it means making them equitable.

These aren't just linguistic quirks—they point to real risks of AI reinforcing the digital divide.
Even as LLMs become widespread, they're not being used—or served—equally.

📊 Higher-SES users:
– Use more abstract & concise prompts
– Focus on topics like "inclusivity" & "travel"
– Use AI for work and study related queries
📎 Lower-SES users:
– Use more concrete language
– Personify the AI more (e.g., “hello”, “thank you”)
– Ask more practical, day-to-day questions

We surveyed 1,000 people from diverse SES backgrounds and analyzed 6,482 prompts from their real previous interactions with LLMs.
What we found: SES significantly shapes how people use and experience generative AI.

🚨 New paper accepted at #ACL2025 Main conference! 🙌
"The AI Gap: How Socioeconomic Status Affects Language Technology Interactions"
w/ @amandacurry.bsky.social & @dirkhovy.bsky.social

Very happy for this first collab with @milanlp.bsky.social 🤝

🔗 lnkd.in/dtsH3gaX
🤗 lnkd.in/d7diuBJh

🧵👇
#ACL2025

The @milanlp.bsky.social lab is presenting 6 papers at #NAACL2025!

Welcome to the team Amelie! We are very happy to have you with us 🥳🇩🇰

Last week, our PhD student @brtrm.bsky.social presented "Improving Reasoning Performance in Large Language Models via Representation Engineering" at ICLR 2025 🤖💭

If you missed his presentation, check out the paper here arxiv.org/abs/2504.19483

#NLProc #ICLR2025

📖For today's Reading Group @elisabassignana.bsky.social presented "Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates" by Aida Davani et al.

Paper: dl.acm.org/doi/10.1145/...

#NLProc

Very happy that Federica visited us from Milano-Bicocca on Friday! Very inspiring talk about the perception of social class stereotypes from the perspective of social psychology 💭🤖

For our last Friday's @milanlp.bsky.social lab seminar, it was a pleasure to have @lajello.bsky.social presenting "Persuasive Agents and their Collective Biases".

#NLProc