What are the interaction dynamics between Parametric Knowledge and Context Knowledge in generating longer Natural Language Explanation sequences? Check out our recent preprint investigating this ⤵️ #NLProc #XAI @sekh-copenlu.bsky.social @apepa.bsky.social @copenlu.bsky.social

Attending EMNLP 2025 this week? So is CopeNLU -- come find us there! ⤵️ www.copenlu.com/news/8-paper... @apepa.bsky.social @rnv.bsky.social @kirekara.bsky.social @shoejoe.bsky.social @dustinbwright.com @zainmujahid.me @lucasresck.bsky.social @iaugenstein.bsky.social #NLProc #AI #EMNLP2025

Heading to #EMNLP2025? Interested in automatic summarization? Then come to our poster for "Unstructured Evidence Attribution for Long Context Query Focused Summarization" ! ⏰ When: Fri. Nov 7 14:00-15:30 🗺️ Where: Hall C I'm unable to attend but @iaugenstein.bsky.social will present our work!

⏲️ 🎓 Only a few days left to apply to do a PhD in Natural Language Processing with @apepa.bsky.social and me @copenlu.bsky.social @aicentre.dk! #NLProc #ML #XAI #phdpositions #academicjobs

Which, whose, and how much knowledge do LLMs represent? I'm excited to share our preprint answering these questions: "Epistemic Diversity and Knowledge Collapse in Large Language Models" 📄Paper: arxiv.org/pdf/2510.04226 💻Code: github.com/dwright37/ll... 1/10

Looking for PhD opportunites in #NLProc #XAI? We @copenlu.bsky.social @aicentre.dk @apepa.bsky.social are hiring for a start in Spring or Autumn 2026. 📆 Application deadline: 31 October 2025 ℹ️ Details: www.copenlu.com/news/phd-fel... 👀 Reasons to apply: www.copenlu.com/post/why-ucph/

📣 Looking for PhD opportunities in Natural Language Processing? Our group has several openings for a start in Spring or Autumn 2026 -- apply by 31 October: www.copenlu.com/news/phd-fel... #NLProc #XAI @copenlu.bsky.social @apepa.bsky.social @aicentre.dk

Thrilled to announce that my survey paper has been accepted at #EMNLP2025 Main! 🎉 To our knowledge, this is the first comprehensive survey dedicated to multilingual explainability. 📄 Preprint: openreview.net/forum?id=KQj... w/ Anna Korhonen, @iaugenstein.bsky.social #NLP #ExplainableAI

🎉 Our work on attribution in summarization is now accepted to #EMNLP2025 main! 🎉 "Unstructured Evidence Attribution for Long Context Query Focused Summarization" w/ @zainmujahid.me , Lu Wang, @iaugenstein.bsky.social , and @davidjurgens.bsky.social

Happy to share that our work on multi-modal framing analysis of news was accepted to #EMNLP2025! Understanding news output and embedded biases is especially important in today's environment and it's imperative to take a holistic look at it. Looking forward to presenting it in Suzhou!

🙋 How do Large Language Models internally process cultural knowledge? 🌐 Happy to share our new preprint "Entangled in Representations: Mechanistic Investigation of Cultural Biases in Large Language Models" 📃 Paper: arxiv.org/abs/2508.08879

🚀 Excited to share our new preprint: BiasGym: Fantastic LLM Biases and How to Find (and Remove) Them 📄 Read the paper: arxiv.org/abs/2508.08855

Thanks for everyone who came to our #acl2025nlp presentations (even the informal ones). Hope to connect again at #emnlp2025! #NLProc @siddheshp.bsky.social @lovhag.bsky.social @saravera.bsky.social @nadavb.bsky.social @gretawarren.bsky.social @iaugenstein.bsky.social

Meet @iaugenstein.bsky.social, Prof at University of Copenhagen 🇩🇰, ELLIS Scholar, and member of ELLIS Unit Copenhagen (@aicentre.dk) + ELLIS Program #NLProc. Her advice to young women in science: “Success isn't just about tech skills. It's also about managing your career.” #WomenInELLIS

CopeNLU will give five paper presentations and one invited talk at #ACL2025NLP this week ⤵️ @apepa.bsky.social @rnv.bsky.social @nadavb.bsky.social @iaugenstein.bsky.social @gretawarren.bsky.social @saravera.bsky.social @lovhag.bsky.social @zainmujahid.me @siddheshp.bsky.social

Thanks to everyone who joined us @aicentre.dk for the Pre-ACL 2025 workshop! We had 7 inspiring keynotes, 26 poster presentations, and there was time for informal mingling as well. Thanks to DSSA for the generous support. See some of you in Vienna for #acl2025nlp! #NLProc aicentre.dk/events/pre-acl

🎓 Looking for PhD opportunities in #NLProc for a start in Spring 2026? 🗒️ Add your expression of interest to join @copenlu.bsky.social here by 20 July: forms.office.com/e/HZSmgR9nXB Selected candidates will be invited to submit a DARA fellowship application with me: daracademy.dk/fellowship/f...

The LEADING reporting guideline is now published in Comprehensive Psychiatry 🥳 See www.sciencedirect.com/science/arti... Or read the previous summary 👇

⏰ Poster submission deadline TODAY for the [email protected] Workshop 🇩🇰 📅 We've finalised our schedule and speakers: Thamar Solorio, Smaranda Muresan, @davidjurgens.bsky.social, Nanyun Peng, @danishpruthi.bsky.social , Kai-Wei Chang, and Mausam www.aicentre.dk/events/pre-a... @aicentre.dk

Join us in Copenhagen for the Pre-ACL 2025 Workshop! 🇩🇰 We’re excited to welcome researchers and practitioners in Natural Language Processing, Generative AI, and Language Technology to a one-day workshop on 26 July 2025 – just ahead of ACL 2025 in Vienna. Learn more: www.aicentre.dk/events/pre-a...

⏰ Only one week left to apply for this fully funded PhD fellowship at the University of Copenhagen & @aicentre.dk ! Don’t miss the chance to explore interpretability for LLMs under my and @iaugenstein.bsky.social's supervision @copenlu.bsky.social

@iaugenstein.bsky.social has been crowned last year’s winner of the Karen Spärck Jones Award. Her well-deserved trophy was awarded after delivering a very insightful keynote at ECIR 2025. Read our article in BCS Informer. medium.com/bcs-irsg-inf... We're seeking nominations for the next KSJ Award!

Lastly, we present "Measuring and Benchmarking LLMs' Capabilities to Generate Persuasive Language", finding that personas in system prompts change persuasiveness substantially, even when only instructed to paraphrase #NAACL2025 #NLProc @iaugenstein.bsky.social arxiv.org/abs/2406.17753

In "Investigating Human Values in Online Communities", we perform a high-scale study of the unique values expressed by online communities with different perspectives arxiv.org/abs/2402.14177 #NAACL2025 #NLProc @nadavb.bsky.social @rnv.bsky.social @frimelle.bsky.social @iaugenstein.bsky.social

C3NLP Workshop #NAACL2025: @iaugenstein.bsky.social will be presenting on tailoring LLM outputs to cultures, including where implicit cultural personalisation based on names leads to over-simplification arxiv.org/abs/2502.11995 @rnv.bsky.social @frimelle.bsky.social bsky.app/profile/frim... #NLProc

@yongcao.bsky.social, Haijiang Liu, @rnv.bsky.social, @iaugenstein.bsky.social, @paul-rottger.bsky.social, @danielhers.bsky.social. Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations. arxiv.org/abs/2502.07068 #NAACL2025 #NLProc

Jingyi Sun, @apepa.bsky.social, @iaugenstein.bsky.social. Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework. arxiv.org/abs/2406.15085 bsky.app/profile/apep... #NAACL2025 #NLProc

The CopeNLU group will be giving four paper presentations and one invited talk at #NAACL2025 this week, on topics including explainable AI and cross-cultural #NLProc Schedule + more details ⤵️ #XAI @apepa.bsky.social @rnv.bsky.social @nadavb.bsky.social @frimelle.bsky.social @iaugenstein.bsky.social

and... the official version of the paper is now out! 📄 dl.acm.org/doi/10.1145/... 🌟 Work with Irina Shklovski & @iaugenstein.bsky.social looking forward to talking all things human-AI interaction, explainability and misinformation this week -- please reach out if you'd like to chat! 🤗

Having an amazing time so far in Yokohama for #CHI2025! 🌸 I'll be presenting our paper, Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking, at the Explainable AI session tomorrow! ✨ 📅 Monday, April 28 | 4:56 PM 📍G303 🔗 programs.sigchi.org/chi/2025/pro...

🎓 Fully funded PhD in interpretable NLP at the University of Copenhagen & @aicentre.dk with @iaugenstein.bsky.social and me, @copenlu.bsky.social 📆 Application deadline: 15 May 2025 👀 Reasons to apply: www.copenlu.com/post/why-ucph/ 🔗 Apply here: candidate.hr-manager.net/ApplicationI... #NLProc #XAI

Many congratulations to the Karen Spärck Jones Award winner @iaugenstein.bsky.social, who gave an exciting keynote on "Understanding the Interplay between LLMs’ Utilisation of Parametric and Contextual Knowledge"! 👏 🎉 We also thank our sponsor @bloomberglp.bsky.social! #ecir2025

I'm so grateful to the British Computing Society & Bloomberg for honouring me with the Karen Spärck Jones Award 🙏 I gave the award lecture on LLMs’ Utilisation of Parametric & Contextual Knowledge at #ECIR2025 today (slides: isabelleaugenstein.github.io/slides/2025_...) www.bcs.org/membership-a...

🚨New pre-print 🚨 News articles often convey different things in text vs. image. Recent work in computational framing analysis has analysed the article text but the corresponding images in those articles have been overlooked. We propose multi-modal framing analysis of news: arxiv.org/abs/2503.20960

Massive congrats to @kirekara.bsky.social for successfully defending his PhD thesis on mitigating reasoning inconsistencies! 🎉 🍾 👏 👏👏 osoblanco.github.io/thesis/ Thanks to @delliott.bsky.social, @barbaraplank.bsky.social & Ivan Titov for serving on the committee. @copenlu.bsky.social @aicentre.dk

Massive congrats to @nadavb.bsky.social for passing his PhD defence yesterday! 👏👏👏 Thanks to Anders Søgaard, @radamihalcea.bsky.social @ricosennrich.bsky.social for serving as examiners. You can find his thesis here, which the committee characterised as "a joy to read": arxiv.org/abs/2503.07395

Thank you to those who came to my lecture on #NLProc fundamentals at #KHIPU2025! You can find my slides here: isabelleaugenstein.github.io/slides/2025_... @khipu-ai.bsky.social

New preprint: "Unstructured Evidence Attribution for Long Context Query Focused Summarization" We propose *unstructured* evidence attribution for long context summarization and a synthetic dataset called SUnsET which can help models perform this task. Paper link: arxiv.org/abs/2502.14409 Thread ⬇️

🚨 Preprint alert 🚨 𝐂𝐚𝐧 𝐂𝐨𝐦𝐦𝐮𝐧𝐢𝐭𝐲 𝐍𝐨𝐭𝐞𝐬 𝐑𝐞𝐩𝐥𝐚𝐜𝐞 𝐏𝐫𝐨𝐟𝐞𝐬𝐬𝐢𝐨𝐧𝐚𝐥 𝐅𝐚𝐜𝐭-𝐂𝐡𝐞𝐜𝐤𝐞𝐫𝐬? (arxiv.org/abs/2502.14132) Fact-checking agencies have come under intense scrutiny in recent months regarding their role in combating misinformation on social media.

Check our new work on making natural language explanations more faithful to a model’s reasoning. We combine GNNs + highlight explanations to improve faithfulness! Read more: arxiv.org/pdf/2412.12318 @copenlu.bsky.social

Our work comparing highlight and interactive explanations has been accepted to #NAACL2025! arxiv.org/pdf/2406.15085 Despite being a less explored approach, span interactive explanations outperform other explanation types across multiple dimensions. #XAI #NLProc @copenlu.bsky.social

When I say my name, people start speaking French to me, although my French is basic. That also happens with AI systems. We wrote a whole paper on that, testing across models for presumed cultural identity based on names w/ Siddhesh Pawar @rnv.bsky.social @iaugenstein.bsky.social

How can explainable AI empower fact-checkers to tackle misinformation? 📰🤖 We interviewed fact-checkers & identified explanation needs & design implications for #NLP, #HCI, and #XAI. Excited to present this work with @iaugenstein.bsky.social & Irina Shklovski at #chi2025! arxiv.org/abs/2502.09083

📄 New preprint: "Collecting Cost-Effective, High-Quality Truthfulness Assessments with LLM Summarized Evidence" We show: fact checking w/ crowd workers is more efficient when using LLM summaries, quality doesn't suffer. arxiv.org/abs/2501.18265

📚 How good are language models at utilising contexts in RAG scenarios? We release 🧙🏽‍♀️DRUID to facilitate studies of context usage in real-world scenarios. arxiv.org/abs/2412.17031 w/ @saravera.bsky.social, H.Yu, @rnv.bsky.social, C.Lioma, M.Maistro, @apepa.bsky.social and @iaugenstein.bsky.social ⭐️

Our research group is on BlueSky as well now! Follow us for updates ⤵️ @copenlu.bsky.social @apepa.bsky.social @nadavb.bsky.social @rnv.bsky.social @dustinbwright.com

Was happy to have had the opportunity to present our work on the detection of factual errors in LLMs to the Brazilian AI community at BRACIS 2024! Here are the slides in case anyone is curious: isabelleaugenstein.github.io/slides/2024_... bracis.sbc.org.br/2024/speakers/ #NLProc #XAI

CopeNLU @ #EMNLP2024 — hope you all enjoyed the conference as much as we did 😊🌴 See you again at #ACL2025NLP and #EMNLP2025! #NLProc @rnv.bsky.social, @dwright37.bsky.social, @zeerak.bsky.social

Happening now at #EMNLP2024 ! Come to poster 34 in Jasmine to talk to me, @rnv.bsky.social and Srishti Yadav about LLM political values!

📢 📅 After a long process of soliciting & vetting bids, I'm excited that we've finally been able to reveal the location for #EMNLP2025 -- it'll be at the International Expo Centre, Suzhou, China from 5-9 November 2025. Looking forward to seeing you there! #NLProc #EMNLP2024