We are delighted to welcome @marlutz.bsky.social to our lab over the next few months! 🎉
She'll work on the representation of different demographic groups in LLMs.

#NLProc

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.

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

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

Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers Hanh Nguyen, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.

#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.

Identifying Linguistic Areas for Geolocation Tommaso Fornaciari, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.

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

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

PATS: Personality-Aware Teaching Strategies with LLM Tutors
Aligning tutoring strategies with student personality improves learning interactions.
🗓 Wed, Mar 25
📍 Poster Session 3 (16:30–18:00)
🔗 aclanthology.org/2026.finding...

Can Reasoning Help LLMs Capture Human Annotator Disagreement?
Across 60 setups, reasoning methods actually hurt disagreement modeling—especially in high-variance cases where humans genuinely disagree.
🗓 Fri, Mar 27
📍 Salle La Palmeraie
🔗 aclanthology.org/2026.eacl-lo...

Exploring Subjective Tasks in Farsi (#WASSA)
Farsi is under-resourced for subjective NLP tasks (sentiment, emotion, toxicity). The key issue isn’t just more data—but better, more representative data.
🗓 Sun, Mar 29
📍 Poster Hall
🔗 aclanthology.org/anthology-fi...

Do LLMs Adapt to Socioeconomic Language Variation? (#VarDial)
LLMs only weakly adapt to SES differences—and often default to higher-SES styles, sometimes producing caricatures.
🗓 Sun, Mar 29
📍 Poster Hall

The Pluralistic Moral Gap
LLMs align with human moral judgments when consensus is high—but fail when opinions diverge, relying on a narrower set of values.
🗓 Wed, Mar 25
📍 Pavillon de Rabat

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...

🗣️ 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

Only 3 days to go until the deadline!

Dense Node Representation for Geolocation Tommaso Fornaciari, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.

#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

Geolocation with Attention-Based Multitask Learning Models Tommaso Fornaciari, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.

#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

How does an LLM’s past influence its future?🤔

In new work, led by @adisimhi.bsky.social, together with @fbarez.bsky.social @boknilev.bsky.social and Shay Cohen, we find conversational history creates a latent "geometric trap" which makes old habits e.g. hallucinations hard to break!

The Social and the Neural Network: How to Make Natural Language Processing about People again Dirk Hovy. Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media. 2018.

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

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

Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning Sotiris Lamprinidis, Daniel Hardt, Dirk Hovy. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018.

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

📢 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

Comparing Bayesian Models of Annotation Silviu Paun, Bob Carpenter, Jon Chamberlain, Dirk Hovy, Udo Kruschwitz, Massimo Poesio. Transactions of the Association for Computational Linguistics, Volume 6. 2018.

#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.

Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting Dirk Hovy, Christoph Purschke. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018.

#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

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

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