For today's reading group, @veraneplenbroek.bsky.social presented "Old Habits Die Hard: How Conversational History Geometrically Traps LLMs" by Simhi et al. (2026) Paper: arxiv.org/abs/2603.03308 #NLProc

Great question. Yes, this should be possible, and we are currently experimenting with this as well in a project. Happy to follow up once we have indications. Feel free to DM

Could not be prouder of @zeerak.bsky.social for this accomplishment: from first paper ever (based on an MSc thesis) to 10-year ToT award. We could not have anticipated the lasting impact of this paper, but it's a great honor – and a wonderful story for any student/advisor team (see Zee's thread).

#MemoryModay #NLProc Fornaciari et al.'s 2022 'Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa' is a useful Python tool for benchmarking NLP predictions with bootstrapped sampling. aclanthology.org/2022.acl-dem...

🧠🤖 It was a pleasure to host @andreadevarda.bsky.social for his talk, "Large Language Models as Models of Human Language(s) and Higher-Level Cognition." A truly inspiring talk! #NLProc

🏆 Congrats to @zeerak.bsky.social and @dirkhovy.bsky.social on the 2016 Test of Time Award! 🎉 "Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter" has shaped research on #hatespeech! Paper: aclanthology.org/N16-2013/ #NLProc

@milanlp.bsky.social x #WomeninAI

For our last reading group, @pranav-nlp.bsky.social presented "Enhancing University Curricula with Integrated AI Ethics Education: A Comprehensive Approach" by Deb et al. (2025) Link: dl.acm.org/doi/10.1145/... #AIEthics #NLProc

#TBT #NLProc Bergman et al.'s 'Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design' explores AI launch with a value-sensitive lens. aclanthology.org/2022.sigdial...

#MemoryMonday #NLProc 'Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists' by Attanasio et al. redefines bias reduction in #AI, sans prior term knowledge. #2022Publication aclanthology.org/2022.finding...

Very happy to have given my first keynote at an #NLProc related conference! This morning at CORIA-TALN 2026 in Nantes, I talked about emerging risks and research directions around the everyday use of LLMs. coria-taln-2026.ls2n.fr/conferences-...

For today's reading group, @esradonmez.bsky.social presented "RLHF May Not Reflect Genuine Preferences" by Ghafouri et al. (2026). Interesting thoughts on whether annotations are actually real preferences! Paper: arxiv.org/abs/2604.03238 #NLProc #RLHF

#TBT #NLProc Hessenthaler et al.'s 2022 work delves into AI's link with fairness & energy reduction in English NLP models, challenging bias reduction theories. #AI #NLP #sustainability aclanthology.org/2022.emnlp-m...

#MemoryMonday #NLProc 'BERTective: Language Models and Contextual Information for Deception Detection' by Fornaciari, T. et al. (2021) explores AI's ability to detect deceit through context. www.aclweb.org/anthology/20...

For today's reading group, @marlutz.bsky.social presented "State media control influences large language models" by Waight et al. (2026) Paper: www.nature.com/articles/s41... #NLProc

#TBT #NLProc 'Exploring challenges in Zero-shot Cross-lingual Hate Speech Detection, @deboranozza.bsky.social (2021) reveals how current models may inaccurately label non-hateful, language-specific interjections as hate speech signals.' aclanthology.org/2021.acl-sho...

It's likely getting worse before it gets better. 5 deadlines mean lots of pressure on both ends. One radical idea: limit to 2 ARR submissions & conferences a year + abolish the short paper. That eases the pressure off everyone to always send, and gives more time for longer, more thoughtful papers.

We were honored to welcome Giulia Barbareschi to our lab for an inspiring conversation on inclusive technology and what NLP should learn from it. Thank you for sharing your insights and vision! #InclusiveTech #Accessibility #NLProc

#MemoryMonday #NLProc 'MilaNLP @ WASSA: Does BERT Feel Sad When You Cry?' by Fornaciari et al. (2021) indicates that emotion and empathy are not related tasks for prediction. aclanthology.org/2021.wassa-1...

For today's reading group, Urs Zaberer presented "Toward universal steering and monitoring of AI models" by Beaglehole et al. (2026) Paper: www.science.org/doi/10.1126/... #NLProc

#TBT #NLProc 'Universal Joy: A Data Set and Results for Classifying Emotions Across Languages' by Lamprinidis et al. (2021) explores how AI research affects our planet. Tech can be green too! #SustainableTech aclanthology.org/2021.wassa-1.7

#MemoryMonday #NLProc Uma, A. N. et al. examine AI model training in 'Learning from Disagreement: A Survey'. Disagreement-handling methods' performance is shaped by evaluation methods & dataset traits. www.jair.org/index.php/ja...

On the heels of a fantastic Dagstuhl seminar on Social Intelligence in AI (thx, @jennhu.bsky.social, @maartensap.bsky.social, @tomerullman.bsky.social, & Lucie Flek), a callback to how we thought about this 5 years ago.

@taniseceron.bsky.social is presenting her work about political content in pre-training and post-training data at the AI & Society conference. #AIandSociety #NLProc

#TBT #NLProc 'Importance of Modeling Social Factors of Language: Theory and Practice' by @dirkhovy.bsky.social, Diyi Yang discusses NLP limitations, calling for focus on social factors, not just content. aclanthology.org/2021.naacl-m...

Last Friday, we had the pleasure of hosting Clement Jonathan Mazet-Sonilhac and Monika Kaczorowska for an insightful discussion on AI adoption and its impact on the quality of financial services. #NLProc #AI

#MemoryModay #NLProc 'Measuring Hurtful Sentence Completion in Language Models' by @debora_nozza et al. introduces HONEST, a new metric for harmful stereotypes. Language models use hurtful words 4.3% of the time.

For today's reading group, @pia-p.bsky.social presented "When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning" by Yijiang River Dong et al. (2025) Paper: aclanthology.org/2025.finding... #NLProc

#TBT #NLProc F. Bianchi & Dirk Hovy's 2021 paper points out 5 barriers in NLP research and suggests solutions. Details on risks, biases & costly trials here:

🎉 Excited to welcome Lorena Calvo Bartolomé to our lab! Her expertise in NLP and signal processing will bring fresh perspectives to our research. She will be working on TOLD, a project exploring voice-based data collection as a richer alternative to written annotation. #NLProc

#MemoryModay #NLProc 'Five Sources of Bias in Natural Language Processing' by Dirk Hovy and Shrimai Prabhumoye. It outlines 5 bias sources in NLP: data, annotation, input, models, design. Info = fairness! #AIEthics

We had the pleasure of hosting @tresiwald.bsky.social and Alireza Salemi at our latest seminar. Andreas spoke about the reliability of language models through computational argumentation, while Alireza presented his work on personalizing LLMs. Thank you both for the inspiring talks! #NLProc

Welcome @esradonmez.bsky.social! We’re excited to have her with us over the next few months, where she’ll be working on pluralistic alignment.

Had a good time at #LREC in Palma!

#LREC2026 in Palma was a wonderful experience! I had the opportunity to reconnect with old friends and make new ones 🫰 I was also honored to give a keynote to the Identity-Aware NLP Workshop on the risks and research directions surrounding the everyday use of LLMs

For today's reading group, @knewmikel.bsky.social presented "Multitask-Bench: Unveiling and Mitigating Safety Gaps in LLMs Fine- tuning" by Essa Jan et al. (2025) Paper: aclanthology.org/2025.coling-... #NLProc

#TBT #NLProc 'FEEL-IT: Emotion and Sentiment Classification for the Italian Language' by Federico Bianchi, @debora_nozza, Dirk Hovy (2021) presents FEEL-IT, a novel model for Italian emotion detection and sentiment analysis.

Sending beach vibes, recently @milanlp.bsky.social attended #LREC in beautiful Palma! #NLProc

#MemoryModay #NLProc Bianchi et al.'s 'Cross-lingual Contextualized Topic Models with Zero-shot Learning' introduces a language-neutral model that predicts topics in unseen languages. Improves coherence and stability. www.aclweb.org/anthology/20...

#TBT #NLProc Bianchi, Terragni & Dirk Hovy present a smarter technique for topic modeling. Their method uses contextual embeddings for clear, meaningful word clusters, transforming how we interpret large text collections.

#MemoryModay #NLProc 'We will Reduce Taxes' - Identifying Election Pledges with Language Models' by Fornaciari et al. makes election promise tracking effortless with neural models.

#TBT #NLProc Check out 'Helpful or Hierarchical?' by Rashid, F. et al advocating better non-binary representation in tech. #Inclusion

#MemoryModay #NLProc 'Visualizing Regional Language Variation Across Europe on Twitter' by Dirk Hovy et al. uncovers language differences across Europe with stunning visuals. Language is art! #Linguistics link.springer.com/referencewor...

It was a pleasure to host @marcostranisci.bsky.social and hear about his newly awarded Marie Curie project “DISHARM” - inspiring work and a great discussion! #NLProc

New paper at #LREC2026 🎉 We introduce ACID, a cross-cultural dataset to study classism in NLP. 🔍 Key findings: pervasive negative stereotypes especially concerning morality, frequent offensiveness, and strong individual blame. 🔗 lrec.elra.info/lrec2026-mai...

Great discussion in today’s reading group! 📚 @a-lauscher.bsky.social presented “Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning” Link: arxiv.org/pdf/2511.01490 #NLProc

#TBT #NLProc 'Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview' by Shah, Schwartz, Dirk Hovy (2020). Dive into their mathematical NLP bias framework, its origins, impacts, and types. #AIEthics aclanthology.org/2020.acl-mai...

📚 For today's reading group Yujie Ren presented "Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models" by Cui et al. Paper: arxiv.org/pdf/2411.11496 #NLProc

📚 For today's reading group Serena Pugliese presented "Sycophantic AI decreases prosocial intentions and promotes dependence" by Cheng et al. (2026) Paper: www.science.org/doi/10.1126/... #NLProc

We were thrilled to host @alexanderhoyle.bsky.social at our lab! His insightful talk on topic modeling sparked great discussions and fresh perspectives across the team. Thanks for the visit, we hope to welcome you back soon! #NLProc