For today's Reading Group @carolin-holtermann.bsky.social presented "REL-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance" by @kaitlynzhou.bsky.social and colleagues. Paper: aclanthology.org/2025.naacl-l... #NLProc

#MemoryModay #NLProc Uma et al. (2020) highlights 'A Case for Soft Loss Functions' efficacy using soft labels & crowd annotations in AI tasks, outshining top-tier methods.

#TBT #NLProc '[MASK]? Making Sense of Language-Specific BERT Models' by @deboranozza.bsky.social, Bianchi & @dirkhovy.bsky.social (2020), explores language-specific vs universal BERT models.

I realized how much DMing is like being a professor/chairing a committee. You: - make a brilliant plan for 2+ hours of fun - prep lots of material - immediately get derailed by questions/arguments/etc. - keep it together to make the most of the time together - end up not using most of the material

- Optional: question your life choices but show up to do it again the next week anyway

#MemoryModay #NLProc 'Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers,' by Nguyen & @dirkhovy.bsky.social decodes speaker reviews for user preferences using topic models. Domain knowledge needed for market analysis.

For today’s lab seminar, we had the pleasure of hearing an inspiring talk by Heather Lent on Emerging Ethical Challenges in NLP Research and NLP Security, wherein researchers should strive to uphold the ethical best practices of both NLP and cybersecurity. #NLProc

We're excited to welcome @pia-p.bsky.social who will be visiting our lab for the upcoming months! She is working on personalizing content moderation beyond sociodemographics. #NLProc

#TBT #NLProc Fornaciari, @dirkhovy.bsky.social's 'Identifying Linguistic Areas for Geolocation' explores using social media writing for geolocation via Point-to-City (P2C).

LLMs are reshaping how we process information, now even processing videos for us. In a study with 900+ participants, we found AI boosts efficiency and accuracy, but also drives overreliance. So the real question: how much of our access to information are we willing to outsource to LLMs?

Wish I could be at @eaclmeeting.bsky.social, but the lab is well represetned. If you are there, come and say hi!

Thinking of applying for an #MSCA Postdoctoral Fellowship in 2026? I’m open to supervising at Bocconi! Feel free to reach out. By submitting an expression of interest to Bocconi, selected applicants will receive full proposal support. 🗓️ Deadline: April 15 👉 www.unibocconi.it/en/horizon-e...

Excited to share that @milanlp.bsky.social will be presenting 5 new papers at #EACL2026 and workshops in Rabat 🇲🇦!

Only 3 days to go until the deadline!

🗣️ Last Friday, we had the pleasure of hosting @dustinbwright.com for an insightful talk on “LLMs Lack Perspective and Epistemic Diversity.” The talk explored how diverse are the information and perspectives that people are being exposed to in this new era. #NLProc

#MemoryModay #NLProc 'Dense Node Representation for Geolocation' by Fornaciari & @dirkhovy.bsky.social reveals efficient geolocation methods using node2vec & doc2vec models. Greater network size, less parameters.

📚Yesterday in our reading group, Mareike Lisker presented "Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)" by Liwei Jiang et al. (2025) Paper: arxiv.org/pdf/2510.22954 #NLProc

#TBT #NLProc 'Geolocation with Attention-Based Multitask Learning Models' by Tommaso Fornaciari, @dirkhovy.bsky.social (2019) reveals how online political talks can become one-sided. Breaking out of our bubbles! #SocialMedia

#MemoryModay #NLProc 'Make Natural Language Processing About People Again' by @dirkhovy.bsky.social (2018) uncovers how AI models portray different religions and emotions. #AIEthics

Joel Tetreault (not on here) also has a great talk on the topic, with lots of interesting anecdotes

#TBT #NLProc 'Predicting News Headline Popularity' by Lamprinidis, Hardt, @dirkhovy.bsky.social (2018) shows neural networks perform similar to Logistic Regression in prediction.

One of my favorite studies of the last few years! Great read (albeit with a side of worrying implications for surveys)

This week in our reading group @taniseceron.bsky.social presented “Linear Representations of Political Perspective Emerge in LLMs”. A study investigating how political biases are encoded in internal representations. 🧠 Paper: arxiv.org/abs/2503.02080 #NLProc

📢 Call for Abstracts! Towards a Safer Web for Women (co-located with #WebSci26) 📍 Braunschweig 🇩🇪 | 26 May 2026 Theme: Preventive approaches to women’s online safety 🗓 Deadline: 27 March 2026 🔗 forms.gle/tYheEgSwGecf... 🌐 tsww26.github.io

#MemoryModay #NLProc 'Comparing Bayesian Models of Annotation' by Paun et al. dives into corpus annotation, evaluating six models' predictiveness and accuracy. Essential for navigating annotators and item difficulties.

One of my favorite interdisciplinary projects (with @questoph.bsky.social). Plus: colorful maps!

#TBT #NLProc 'Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting' by @dirkhovy.bsky.social and Christoph Purschke (2018) highlights how social class and background impact technology performance. #TechInclusion

For today's reading group, Lasse Jantsch presented "Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers" by Adam Karvonen et al. (2026) Paper: arxiv.org/abs/2512.15674 #NLProc

Spending the week in Paris at #IASEAI 2026, joining colleagues for conversations on the present and future of safe and ethical AI.

We were thrilled to host @mtutek.bsky.social at our lab last week. His talk "From Internals to Integrity: How Insights into Transformer LMs Improve Safety, Interpretability, and Explanation Faithfulness" led to great discussions! 👏 #Transformers #AISafety #ExplainableAI #MLResearch #NLProc

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

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.

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

Honored to give my first keynote at #IRCDL2026 on February 19th. I’ll talk about how LLMs have shifted from productivity tools to everyday sources of info & personal guidance and what that means for risk, trust, bias, and alignment. ircdl2026.unimore.it

We were excited to host @naitian.org at today’s lab seminar for a talk on variation, semiotics, fashion, and style. A refreshing perspective at the intersection of sociolinguistics and NLP! #NLProc

For today's reading group @elisabassignana.bsky.social presented "How AI Impacts Skill Formation" by Judy Hanwen Shen & Alex Tamkin (2026). Paper: arxiv.org/pdf/2601.20245 #NLProc

🧠For this week’s lab seminar, @boleima.bsky.social talked about how survey methodology can inform NLP research, from annotations to human–AI alignment. #NLProc

For today's reading group, @deboranozza.bsky.social presented "LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users" by Elinor Poole-Dayan et al. Paper: arxiv.org/pdf/2406.17737 #NLProc

Last week we welcomed Nikhil Sharma to our lab seminar for a talk on Information Seeking, Consumption and Dissemination with LLM-powered Information Systems. #NLProc #HCI

#TBT #NLProc 'SAFETYKIT: Measuring Safety in Open-domain Conversational Systems' by Dinan et al. (2022) introduces taxonomy for AI safety, assesses tools' limits. #AIsafety

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

New year, new job? If that is your current mantra, check the open postdoc positions with Debora Nozza and me at our lab. Deadline is January 31st. milanlproc.github.io/open_positio...

#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

The deadline is approaching! Join the team :)

🚨(Software) Update: In my PhD, I had a side project to fix an annoying problem: when you ask 5 people to label the same thing, you often get different answers. But in ML (and lots of other analyses), you still need a single aggregated answer. Using the majority vote is easy–but often wrong. 1/N

However, disagreement isn’t just noise—it’s information. It can mean an item is genuinely hard—or someone wasn’t paying attention. If only you knew whom to trust… That summer, Taylor Berg-Kirkpatrick, Ashish Vaswani, and I built MACE (Multi-Annotator Competence Estimation). 2/N

MACE estimates: 1. Annotator reliability (who’s consistent?) 2. Item difficulty (which examples spark disagreement?) 3. The most likely aggregate label (the latent “best guess”) That “side project” ended up powering hundreds of annotation projects over the years. 3/N

I always wanted to revisit it, port it from Java to Python & extend to continuous data, but never found the time. Last week, I played around with Cursor – and got it all done in ~1 hour. 🤯 If you work with any response data that needs aggregation, give it a try—and let me know what you think! 4/N

If you are curious about the theoretical background, see Hovy, D., Berg-Kirkpatrick, T., Vaswani, A., & Hovy E. (2013). Learning Whom to Trust With MACE. In: Proceedings of NAACL-HLT. ACL. aclanthology.org/N13-1132.pdf And for even more details: aclanthology.org/Q18-1040.pdf N/N

I included some test cases on GitHub, will look if I still have the ones we used in the paper.