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

#TBT #NLProc 'Classist Tools: Social Class Correlates with Performance in NLP' by Curry et al. (2024) explores AI's hidden energy problem, and how machine learning impacts environmental sustainability. Tech can be green! #CleanTech

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

#MemoryModay #NLProc 'Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection' - Attanasio et al. Explores reliability of interpretability in hate speech detection.

#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

📖For this Thursday's Reading Group @elisabassignana.bsky.social presented "The sociolinguistic foundations of language modeling" by Grieve et al. Paper: www.frontiersin.org/journals/art... #NLProc #LLM #sociolinguistics

#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. /publication/2019_m2v/2019_m2v

🎓We're back with Fridays' lab seminars! Today we had Suyash Fulay presenting "Truth, Political Bias, and AI Representation". #NLProc

#TBT #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.

📖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

#MemoryModay #NLProc 'My Answer is C' by Wang et al. (2024) underscores the scrutiny needed for full text responses in LLMs multi-choice evaluations.

#TBT #NLProc 'Temporal and Second Language Influence on Intra-Annotator Agreement and Stability in Hate Speech Labelling' Abercrombie, @dirkhovy.bsky.social, & Prabhakaran (2023). NLP models: inclusive or not?

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

#MemoryModay #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.

#TBT #NLProc Outstanding Paper at ACL 2024! 'Towards More Meaningful Evaluations for Values and Opinions in Large Language Models' by @paul-rottger.bsky.social et al. Enhancing political bias evaluation.

#MemoryModay #NLProc 'Detecting Misogynous Memes with Text & Image Modalities' by Attanasio, @deboranozza.bsky.social, Bianchi. Their novel system uses Perceiver IO, surpassing all previous benchmarks.

#TBT #NLProc 'XLM-EMO: Multilingual Emotion Prediction in Social Media Text' by Bianchi, @deboranozza.bsky.social, @dirkhovy.bsky.social (2022) advances cross-language emotion detection, especially for low-resource languages.

#MemoryModay #NLProc Plaza-del-Arco, @debora_nozza, @dirkhovy.bsky.social's 2024 paper "Wisdom Instruction-Tuned Language Model Crowds" shows that multiple LLMs can be BETTER than a single model & specialize across tasks & languages.

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

#MemoryModay #NLProc #TBT #NLPproc 'Pipelines for Social Bias Testing of Large Language Models' by @deboranozza.bsky.social, Federico Bianchi, @dirkhovy.bsky.social (2022). Proposes social bias tests akin to software testing in AI dev pipelines.

#TBT #NLProc Paper: 'Multi-dimensional Study on Bias in Vision-Language Models' by G. Ruggeri, @deboranozza.bsky.social 2023. Unveils biases in VL models affecting tasks.

#MemoryMonday #NLProc 'Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks' by @paul-rottger.bsky.social et al. (2022) explores descriptive and prescriptive data labeling paradigms.

🔴 LIVE NOW: The first keynote of the Gender Bias in NLP workshop! @a-lauscher.bsky.social is telling A Fairy Tale of Gender in Language Technology. #ACL2025 #GeBNLP #NLP

#TBT #NLProc Plaza-del-Arco et al.'s 'Divine LLaMAs..' (2024) addresses stereotypes on religion in Large Language Models and their social impact. Tech for all! #DigitalEquity

We are very honored to have @dirkhovy.bsky.social as General Chair of #EMNLP2025, which will take place in Suzhou, China. Looking forward to a great conference!

We’re incredibly proud to announce that our lab received two #ACL2025 awards: Best Social Impact Paper for @elisabassignana.bsky.social and @dirkhovy.bsky.social , and Outstanding Paper for @paul-rottger.bsky.social. Congratulations to them and to all collaborators who made this possible!

@milanlp.bsky.social @ #ACL2025 in #Vienna! #NLProc

#MemoryMonday #NLProc Attanasio et al.'s "Twists, Humps, and Pebbles" paper (which won Social Impact Award) reveals disparities in speech models across 19 languages! 🌍🗣️

Let me know if I missed anything in the timetables, and please say hi if you want to chat about sociotechnical alignment, safety, the societal impact of AI, or related topics :) Here is a link to the timetable sheet 👇 See you around! docs.google.com/spreadsheets...

Finally, I will be with @carolin-holtermann.bsky.social and @a-lauscher.bsky.social to present our work on evaluating geotemporal reasoning ability in LLMs. This will be in the Wednesday 1100 poster session: aclanthology.org/2025.acl-lon...

I will also be at @tiancheng.bsky.social's oral *today at 1430* in the SRW. Tiancheng will present a non-archival sneak peek of our work on benchmarking the ability of LLMs to simulate group-level human behaviours: bsky.app/profile/tian...

Otherwise, you can find me in the audience of the great @manueltonneau.bsky.social oral *today at 1410*. Manuel will present our work on a first global representative dataset of hate speech on Twitter: bsky.app/profile/manu...

Finally, there's a couple of papers on *LLM persuasion* on the schedule today. Particularly looking forward to Jillian Fisher's talk on biased LLMs influencing political decision-making!

*pluralism* in human values & preferences (e.g. with personalisation) will also just grow more important for a global diversity of users. @morlikow.bsky.social is presenting our poster today at 1100. Also hyped for @michaelryan207.bsky.social's work and @verenarieser.bsky.social's keynote!

Measuring *social and political biases* in LLMs is more important than ever, now that >500 million people use LLMs. I am particularly excited to check out work on this by @kldivergence.bsky.social @1e0sun.bsky.social @jacyanthis.bsky.social @anjaliruban.bsky.social

Very excited about all these papers on sociotechnical alignment & the societal impacts of AI at #ACL2025. As is now tradition, I made some timetables to help me find my way around. Sharing here in case others find them useful too :) 🧵

#TBT #NLProc 'Ecological Fallacy in Annotation' by Orlikowski et al. (2023) posits that sociodemographics in annotator models have minimal impact on performance.

📖For this Thursday's Reading Group, Serena Pugliese presented "Emergent social conventions and collective bias in LLM populations" by Ariel Flint Ashery et al. (2025) Paper: www.science.org/doi/10.1126/... #NLProc

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

#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.

We are thrilled to announce our keynote speakers for the 6th Workshop on Gender Bias in NLP @ #ACL2025! Please join us in welcoming: 🔹Anne Lauscher @a-lauscher.bsky.social 🔹Maarten Sap @maartensap.bsky.social Full details: gebnlp-workshop.github.io/keynotes.html See you on August 1! ☀️ #NLP #GeBNLP

🎉 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! 🚀

#MemoryMonday #NLProc 'The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising 'Alignment' in Large Language Models' by Kirk et al. (2023) presents a novel framework for unpacking 'alignment' in LLMs, promoting definitional clarity.

🎓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

#TBT #NLProc 'Tonneau et al.'s (2024) 'From Languages to Geographies'' reveals geo-cultural bias in hate speech data, underlining the need for improved representation. #Research #BiasInData

📖For this Thursday's Reading Group, Pranav presented "Research Borderlands: Analysing Writing Across Research Cultures" by Bhatt et al. (2025) Paper: arxiv.org/pdf/2506.00784 #NLProc

Just wanted to mention that besides me rattling on about speech, social biases, and NLP in the coziest of environments, that TV starred in a blazing karaoke night just a few hours earlier 🎙️ Thanks again for the invitation @milanlp.bsky.social :)

#MemoryMonday #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.'

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

#TBT #NLProc Metrics for What, Metrics for Whom: Assessing Actionability of Bias Evaluation Metrics in NLP" by Delobelle, Attanasio, @deboranozza.bsky.social, Blodgett, and Talat, 2024) highlights the need for clearer, actionable bias measures in NLP.