For today's reading group @arimuti.bsky.social presented "SPeCtrum: A Grounded Framework for Multidimensional Identity Representation in LLM-Based Agent" by @keyeun.bsky.social.
#NLProc #identity
This year’s workshop places a strong emphasis on preventive rather than reactive approaches to women’s online safety. We invite submissions presenting new findings, recent work, new ideas or previously published research (non-archival) that fits the workshop theme.
Call for abstracts! (Deadline: 17 March)
Submissions are now open for the second edition of Towards a Safer Web for Women Workshop, taking place on 26 May at the Web Science Conference 2026 in Braunschweig 🇩🇪.
👉 More info & submission details: tsww26.github.io
For our weekly reading group, Afshin Karimi presented "What Social Media Use Do People Regret? An Analysis of 34K Smartphone Screenshots with Multimodal LLM". Super interesting discussion!
Paper: dl.acm.org/doi/10.1145/...
#NLProc
In academia, class background strongly shapes who advances and who stalls.
#MemoryModay #NLProc
@gattanasio.cc et al. study asks 'Is It Worth the (Environmental) Cost?' analyzing continuous training for language models. Balances benefits, environmental impacts, for responsible use. #AI #Sustainability
arxiv.org/pdf/2210.07365
One of the most persistent challenges for women's health content is the overlap between clinical terminology and platforms' sex-safety filters. Words such as vagina, breast, menstrual cycle, abortion, miscarriage, or sexual pain are standard medical terms. But automated classification systems— particularly those governing Discover feeds and advertising eligibility-often struggle to distinguish between educational health information and adult content. When that happens, legitimate reporting can be flagged as risky, quietly deprioritized, or excluded from recommendation systems altogether. For founders, this often means educational pages don't rank, patient acquisition funnels break, and paid campaigns are rejected before they launch.
Women's health information is increasingly being censored by anti-adult filters, which tag words like "vagina" as porn.
This isn't a new issue, but in an increasingly age-gated internet world, it's about to get a lot worse.
www.forbes.com/sites/gerist...
🎉 MilaNLP 2025 Wrapped 🎉
Lots of learning, building , sharing, and growing together 🌱
#NLProc
The deadline is approaching! Join the team :)
We're also back with the lab's seminar! Today we had Eleonora Mancini presenting her doctoral research "Multimodal AI for Human Expression Understanding".
#NLP #multimodality #speech
🚀 We’re opening 2 fully funded postdoc positions in #NLP!
Join the MilaNLP team and contribute to our upcoming research projects.
🔗 More details: milanlproc.github.io/open_positio...
⏰ Deadline: Jan 31, 2026
Huge thanks to our speakers at last Friday’s lab seminar!
🗣️ @penzo-nicolo.bsky.social on multi-party conversations
🌍 @patriciachiril.bsky.social on NLP for socially grounded research
#NLProc
Another exhausting day in the lab… conducting very rigorous panettone analysis. Pandoro was evaluated too, because we believe in fair experimental design.
We're happy to have @veraneplenbroek.bsky.social at our lab this week! She presented her #EMNLP2025 work "Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization" and shared more of her exciting ongoing work.
#NLProc
What an inspiring week at #EMNLP2025 in Suzhou🇨🇳!
Huge thanks to the organizers and everyone who stopped by our poster/talk!
For our weekly reading group, @joachimbaumann.bsky.social presented the upcoming PNAS article "The potential existential threat of large language models to online survey research" by @
@seanjwestwood.bsky.social.
LLMs require social knowledge to understand implicit misogyny, yet they mostly fail. If you want to know more, come check my poster from 12.30 to 13.30!
Paper: aclanthology.org/2025.finding...
#EMNLP2025
📚 For today’s reading group @arimuti.bsky.social presented Emergent Misalignment: Narrow Finetuning Can Produce Broadly Misaligned LLMs (Betley et al., 2025).
🧩 arxiv.org/abs/2502.17424
#NLProc #AIAlignment #LLMs
📣 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?
📖For our last Reading Group @donyarn.bsky.social presented
"Culture is Everywhere: A Call for Intentionally Cultural Evaluation" by Oh et al.
Paper: arxiv.org/pdf/2509.01301
#NLProc
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
What makes LLMs agree even when they shouldn’t? 🤔
At our last seminar’s lab, Jan Batzner presented The Brief History of LLM Sycophancy as We Know It.
#NLProc #sycophancy #LLM
🎓We're back with Fridays' lab seminars! Today we had
Suyash Fulay presenting "Truth, Political Bias, and AI Representation".
#NLProc
📖For this Thursday's Reading Group @deboranozza.bsky.social
presented two papers on #sycophancy in #LLMs.
Papers: arxiv.org/pdf/2505.13995, arxiv.org/pdf/2310.13548
#NLProc
We're back with the reading group! 🚀
Today @paul-rottger.bsky.social presented The Levers of Political Persuasion with Conversational AI by Hackenburg et al. (2025)
Paper: arxiv.org/pdf/2507.13919
#NLProc
"The "r" in "woman" stands for rights. Auditing LLMs in Uncovering Social Dynamics in Implicit Misogyny" (lead by @arimuti.bsky.social and w. @deboranozza.bsky.social Alberto Barron-Cedeño and Chris Emmery)
@milanlp.bsky.social @ #ACL2025 in #Vienna!
#NLProc
🎉 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! 🚀
🎓For today's lab seminar, we had the pleasure to host
@miriamschirmer.bsky.social with her presentation on Measuring and Reducing the Psychological Impact of Online Harm and Tiago Pimentel with How Much Does Tokenisation Impact Language Models?
#NLProc #onlineharms #tokenisation
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
