#MemoryMonday #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. aclanthology.org/Q18-1040

🌶️ Dirk Hovy from our @MilaNLProc lab will be joining today's #EMNLP2026 plenary panel on "New Missions in NLP Research"! Don't miss it! 🕝 14:30 📍 P1-3

For today's reading group, Carlos Diez-Fenoy presented "Your Students Don't Use LLMs Like You Wish They Did" by Kobler et al. (2026). Paper: aclanthology.org/2026.acl-lo… #NLProc

#TBT #NLProc 'Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting' by Dirk Hovy and Christoph Purschke (2018) highlights how social class and background impact technology performance. #TechInclusion aclanthology.org/D18-1469

We're excited to welcome Tamara Quiroga as a visiting PhD researcher from Chile! She will be exploring how gender-inclusive language shapes gender representation in stories generated by large language models. #NLProc #genderbias

The Role of Implicit and Explicit Demographic Signals in LLM-based Student Assessment 🎓 Explicit demographic information and cues inferred from conversation history can systematically change LLM assessments. 📍 Hall H 🎤 Donya Rooein 🗓️ 26 October 2026, 16:45–18:15

SEAL: SocioEconomic Alignment in LLMs 🦭 How does LLM service quality vary across users’ socioeconomic statuses? We evaluate helpfulness, sycophancy, human likeness, emotion features and text complexity. 📍 NLP for Positive Impact 🗓️ 28 October 2026

Can LLMs Model Incorrect Student Reasoning? 🧩 A reasoning taxonomy applied to math/science LLM traces reveals domain adaptation, learning-science alignment, and failures in solution recovery. 📍 Hall H 🎤 Yanick Zengaffinen 🗓️ 26 October 2026, 11:00–12:30

Overreliance on AI in Information-seeking from Video Content 📺 AI-mediated information access improves accuracy and efficiency, but users quickly become overreliant, leaving them vulnerable. 📍 Hall H 🎤 Elisa Bassignana · Poster 🗓️ 27 October 2026, 11:00–12:30

I Am Multitudes: A Survey and Roadmap for Rethinking Identity in NLP. 📄 Identity is much more than sociodemographics! 🎤 Arianna Muti · Poster 🗓️ 25 October, 16:00–17:30 📍 Hall H

For our weekly seminar, it was a great pleasure to hear @chahatsaidit 's work about social bias and #responsibleAI. #NLProc

#MemoryMonday #NLProc 'Impoverished Language Technology: The Lack of (Social) Class in NLP' by Curry, Talat, Hovy (2024). New tools target harmful content! #OnlineSafety arxiv.org/pdf/2403.03874

For this week reading group, @arimuti presented "Ownership in AI-Assisted Everyday Tasks" by Megan Wei et al. (2026) Paper: arxiv.org/abs/2609.20658 #NLProc

#TBT #NLProc 'Understanding Political Discourse on Twitter through Election Manifestos' Maurer et al. (2024) present a method for predicting party positioning from tweets aclanthology.org/2024.findin…

#MemoryMonday #NLProc Hung et al.'s 2023 paper, 'Can Demographic Factors Improve Text Classification?' finds demographic adaptations of Transformer NLP models don't notably boost performance. aclanthology.org/2023.findin…

#TBT #NLProc  'Classist Tools: Social Class Correlates with Performance in NLP' by Curry et al. (2024) finds NLP tools perform worse on lower-SES speech - higher perplexity, more ASR errors, dialect flagged as "wrong" by grammar checkers. arxiv.org/pdf/2403.04445

What if AI systems weren’t chatbots? 💬 @EliBassignana sparked a lively discussion at our reading group with Ghosh et al.’s FAccT paper (2026). Paper: dl.acm.org/doi/10.1145/38056… #NLProc #NLPEthics #AIEthics

#MemoryModay #NLProc Countering Hateful and Offensive Speech Online - Open Challenges" (Flor Miriam Plaza-Del-Arco, @debora_nozza et al. 2024) presented a tutorial on the challenges and solutions for detecting and mitigating hate speech online. aclanthology.org/2024.emnlp-…