iiinova — where your digital self keeps evolving

Trustworthy AI Lab @tai-lab.bsky.social · 18/06/2026

Today, Urs is presenting a paper on 'Toward universal steering and monitoring of AI models' at @milanlp.bsky.social reading group today.

010

Reposted by Trustworthy AI Lab

MilaNLP Lab @milanlp.bsky.social · 08/05/2026

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

0106

Trustworthy AI Lab @tai-lab.bsky.social · 05/05/2026

Today @esradonmez.bsky.social gave a talk on 'A Specification Framework for Alignment and Literature Review' in our Oberseminar! Esra identifies recurring mismatches in what is treated as an alignment target and how these targets are justified & translated into mechanisms and evaluation practices.

Esra presenting about alignment: A Specification Framework for Alignment and Review

040

Trustworthy AI Lab @tai-lab.bsky.social · 08/04/2026

On May 12, @a-lauscher.bsky.social gives a keynote at the Social Context workshop: socon-nlpsi.github.io A full week for the lab. If you are at #LREC2026, come find us.

010

Trustworthy AI Lab @tai-lab.bsky.social · 08/04/2026

We are also co-organizing the Identity-Aware AI workshop on May 16 (morning session). If your work sits at the intersection of identity, fairness, and NLP, come join us. #LREC2026 identity-aware-ai.github.io

identity-aware-ai.github.io

Identity-Aware AI 2026

120

Trustworthy AI Lab @tai-lab.bsky.social · 08/04/2026

Our paper with @queerinai.com is accepted at the Identity-Aware AI workshop: "Queering the Audits: Community-Based Auditing of AI Harms to Queer Communities." featuring @pranav-nlp.bsky.social and @a-lauscher.bsky.social as authors.

120

Trustworthy AI Lab @tai-lab.bsky.social · 08/04/2026

"Detecting Hallucinations in Authentic LLM-Human Interactions", studying hallucinations in real LLM-human conversations rather than synthetic benchmarks. Work by @yujie-ren.bsky.social, Niklas Gruhlke, @a-lauscher.bsky.social.

110

Trustworthy AI Lab @tai-lab.bsky.social · 08/04/2026

"Issue Detection and Category Classification in Domain-Specific Technical Logbooks", a collaboration with DESY on NLP for scientific infrastructure. Presented by the authors: Afshin Karimi, Ingmar Hartl, and Henrik Tunnermann, @a-lauscher.bsky.social.

110

Trustworthy AI Lab @tai-lab.bsky.social · 08/04/2026

The Trustworthy AI Lab is heading to #LREC2026 in Palma de Mallorca this May with two papers, a workshop paper, a workshop we co-organize, and a keynote. Here is what to expect.

151

Reposted by Trustworthy AI Lab

Anne Lauscher @a-lauscher.bsky.social · 01/04/2026

Some happy news 🎉 I’m happy to share that I’ve been promoted to Full Professor of Trustworthy AI in the Department of Informatics at the University of Hamburg. Very grateful for the amazing team and collaborators who made this possible. @tai-lab.bsky.social Looking forward to the next years!

1211

Reposted by Trustworthy AI Lab

Carolin Holtermann @carolin-holtermann.bsky.social · 24/03/2026

🚨 New paper alert: A new generation of LLMs can now process speech natively. This could expand access for millions excluded by text interfaces, but our research shows a cost: demographic cues in speaker voice can trigger stereotypical model responses. 🎙️⚖️ Paper: arxiv.org/abs/2603.22260

3175

Reposted by Trustworthy AI Lab

UKP Lab @ukplab.bsky.social · 24/02/2026

🎓 𝗣𝗵𝗗 𝗱𝗲𝗳𝗲𝗻𝘀𝗲 𝗰𝗼𝗻𝗴𝗿𝗮𝘁𝘂𝗹𝗮𝘁𝗶𝗼𝗻𝘀 𝘁𝗼 𝗔𝗻𝗱𝗿𝗲𝗮𝘀 𝗪𝗮𝗹𝗱𝗶𝘀! Congratulations to @tresiwald.bsky.social on the successful defense of his dissertation “𝘈𝘯 𝘐𝘯𝘵𝘦𝘨𝘳𝘢𝘭 𝘝𝘪𝘦𝘸 𝘰𝘯 𝘵𝘩𝘦 𝘙𝘦𝘭𝘪𝘢𝘣𝘪𝘭𝘪𝘵𝘺 𝘰𝘧 𝘓𝘢𝘯𝘨𝘶𝘢𝘨𝘦 𝘔𝘰𝘥𝘦𝘭𝘴 𝘧𝘰𝘳 𝘊𝘰𝘮𝘱𝘶𝘵𝘢𝘵𝘪𝘰𝘯𝘢𝘭 𝘈𝘳𝘨𝘶𝘮𝘦𝘯𝘵𝘢𝘵𝘪𝘰𝘯”, held at Technische Universität Darmstadt on February 17th, 2026.

1112

Trustworthy AI Lab @tai-lab.bsky.social · 13/02/2026

Great talk at our Data Science Lab this week! Jakob Prange from UKE presented on "The Language of Addiction": a computational linguistics perspective on child and adolescent psychiatry. Exciting to see interdisciplinary research bridging computational linguistics and mental health.

Jakob Prange from UKE presented on "The Language of Addiction": a computational linguistics perspective on child and adolescent psychiatry. Exciting to see interdisciplinary research bridging computational linguistics and mental health.

030

Reposted by Trustworthy AI Lab

Gabriella Lapesa @gabriellalapesa.bsky.social · 11/02/2026

Deadline extension alert! Identity-aware AI #LREC2026 extended to February 25th! All info at: identity-aware-ai.github.io

identity-aware-ai.github.io

Identity-Aware AI 2026

013

Reposted by Trustworthy AI Lab

Gabriella Lapesa @gabriellalapesa.bsky.social · 29/01/2026

Deadline approaching! Identity-aware AI workshop #LREC2026 identity-aware-ai.github.io, there is time until Feb 20th to submit a short or full paper, with many non-archival options too!

identity-aware-ai.github.io

Identity-Aware AI 2026

163

Reposted by Trustworthy AI Lab

MilaNLP Lab @milanlp.bsky.social · 29/01/2026

For our weekly reading group, Afshin Karimi presented "What Social Media Use Do People Regret? An Analysis of 34K Smartphone Screenshots with Multimodal LLM". Super interesting discussion! Paper: dl.acm.org/doi/10.1145/... #NLProc

063

Reposted by Trustworthy AI Lab

MilaNLP Lab @milanlp.bsky.social · 15/01/2026

Holidays over, reading group resumes 📖 Today Henning Hoffmann presented the paper "Music for All: Representational Bias and Cross-Cultural Adaptability of Music Generation Models" Paper: arxiv.org/pdf/2502.07328 #NLProc

062

Reposted by Trustworthy AI Lab

MilaNLP Lab @milanlp.bsky.social · 23/01/2026

This week at reading group 📚 @pranav-nlp.bsky.social presented "You Cannot Sound Like GPT": Signs of language discrimination and resistance in computer science publishing. Paper: arxiv.org/abs/2505.08127 #NLProc

1106

Trustworthy AI Lab @tai-lab.bsky.social · 29/01/2026

Benefits: 30 days vacation, flexible hours, work-life balance, health programs (EGYM), pension, professional development. Hamburg is a vibrant, international city with a great quality of life! Full details & application: www.uni-hamburg.de/stellenangeb...

uni-hamburg.de

Ausschreibung

000

Trustworthy AI Lab @tai-lab.bsky.social · 29/01/2026

We're looking for researchers passionate about: Ethical & safe generative AI Multilingual/multicultural AI Multimodality & agentic systems Model interpretability Strong pub record in *CL/AI/ML/FAccT conferences etc. valued. We're a dynamic, well-connected team committed to diversity!

100

Trustworthy AI Lab @tai-lab.bsky.social · 29/01/2026

Exciting postdoc opportunity in Trustworthy AI & NLP with @a-lauscher.bsky.social! Work on cutting-edge generative AI while addressing ethics, fairness, multilingualism & sustainability. 3-year position, teaching included. Deadline: March 2 Start: June 1, 2026

132

Trustworthy AI Lab @tai-lab.bsky.social · 21/01/2026

Submission deadline: February 20, 2026 Notification: Late March Workshop: May 16 (hybrid format) We look forward for your submissions!

000

Trustworthy AI Lab @tai-lab.bsky.social · 21/01/2026

You can submit archival papers (4-8 pages) that get published in LREC proceedings, non-archival versions if your paper is published elsewhere, or creative formats like art, poetry, TikToks, blogs, and teaching materials.

100

Trustworthy AI Lab @tai-lab.bsky.social · 21/01/2026

We're looking for works on bias detection and fairness interventions, perspectivism, policymaking, auditing, and related topics that center identity in NLP.

100

Trustworthy AI Lab @tai-lab.bsky.social · 21/01/2026

AI is developed in a way that amplifies the majority. Current approaches harm marginalized communities and ignore identity in AI systems. This workshop challenges the harmful assumption that NLP should treat all humans as the same.

100

Trustworthy AI Lab @tai-lab.bsky.social · 21/01/2026

We are organizing the Identity-Aware NLP Workshop at LREC 2026 (Palma de Mallorca, May 16). #LREC2026 More info: identity-aware-ai.github.io

identity-aware-ai.github.io

Identity-Aware AI 2026

101

Trustworthy AI Lab @tai-lab.bsky.social · 06/01/2026

Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue by @sukannya.bsky.social, @nilsdy.bsky.social, @a-lauscher.bsky.social, and @igurevych.bsky.social.

031

Trustworthy AI Lab @tai-lab.bsky.social · 06/01/2026

SoS: Analysis of Surface over Semantics in Multilingual Text-To-Image Generation by @carolin-holtermann.bsky.social, @floschne-nlp.bsky.social, @a-lauscher.bsky.social.

101

Trustworthy AI Lab @tai-lab.bsky.social · 06/01/2026

TempViz: On the Evaluation of Temporal Knowledge in Text-to-Image Models by @carolin-holtermann.bsky.social, Nina Krebs, and @a-lauscher.bsky.social.

111

Trustworthy AI Lab @tai-lab.bsky.social · 06/01/2026

Glad to announce that three papers from our group got accepted to #EACL2026! The details of the papers are in the thread:

120

Trustworthy AI Lab @tai-lab.bsky.social · 23/09/2025

Check out the paper here: arxiv.org/abs/2509.13835 ✨Congratulations to all the amazing authors of this work ✨: @minhducbui.bsky.social @carolin-holtermann.bsky.social @valentinhofmann.bsky.social @a-lauscher.bsky.social

030

Trustworthy AI Lab @tai-lab.bsky.social · 23/09/2025

“You speak Bavarian? Then you must be uneducated + closed-minded.” 🤯 Not your opinion? Good. But it might be your LLM’s!! 🧵 Check out our #EMNLP2025 paper, where we uncover concerning dialect bias in recent LLMs - including GPT-5. #AI #Bias #Dialect #Fairness #LLM #NLProc #Safety

182

Trustworthy AI Lab @tai-lab.bsky.social · 17/09/2025

Big congratulations to all our talented researchers and collaborators who made this possible, including @carolin-holtermann.bsky.social, @a-lauscher.bsky.social, @pranav-nlp.bsky.social, and our amazing international collaborators! Looking forward to seeing you all in November.

020

Trustworthy AI Lab @tai-lab.bsky.social · 17/09/2025

Excited to share that Data Science Lab Hamburg will be presenting 4 papers at #EMNLP2025 in Suzhou, China! 🇨🇳 Our team has been pushing the boundaries of multilingual AI research. Here's what we're bringing 👇

171

Reposted by Trustworthy AI Lab

EMNLP @emnlpmeeting.bsky.social · 16/09/2025

🪶 #EMNLP2025 is currently seeking applications for Birds-of-a-Feather and Affinity Group Events, as additional networking opportunities for EMNLP participants. 🪶 Please see this page and submit your application before 26 September, 2025 11:59pm (AoE): 2025.emnlp.org/calls/bof/

2025.emnlp.org

Call for Birds-of-a-Feather and Affinity Group Events

Official website for the 2025 Conference on Empirical Methods in Natural Language Processing

143

Reposted by Trustworthy AI Lab

Gender Bias in NLP Workshop @genderbiasnlp.bsky.social · 01/08/2025

🔴 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

0104

Reposted by Trustworthy AI Lab

Gender Bias in NLP Workshop @genderbiasnlp.bsky.social · 01/08/2025

@a-lauscher.bsky.social outlining the magic formula for fighting gender bias in NLP: ✨ critical thinking ✨ transparency ✨ interdisciplinarity ✨ community building And we're putting that last point into practice right now! Come build community with us 🤝 #GeBNLP #NLP #ACL2025

0103

Trustworthy AI Lab @tai-lab.bsky.social · 29/07/2025

📝 We welcome diverse submissions: Long/short papers Creative formats (art, videos, notebooks!) Student projects 🌍 Hybrid format (in-person and online) with mentorship available For more details, view our website!

010

Trustworthy AI Lab @tai-lab.bsky.social · 29/07/2025

Our topics span: 🔍 Personalization & perspectivist methods ⚖️ Bias detection & fairness in LLMs 👥 Sociodemographics in AI systems 🗳️ Modeling socio-political phenomena 🧠 NLP × social psychology 📊 Survey science & AI accountability

120

Trustworthy AI Lab @tai-lab.bsky.social · 29/07/2025

Wondering what makes each of us unique and how AI should handle human diversity? 🤔 We're organizing Identity-Aware AI workshop at #ECAI2025 Bologna on Oct 25. Deadline: Aug 22 Website: identity-aware-ai.github.io

Identity-Aware AI Workshop announcement. Co-located with ECAI 2025 in Bologna on October 25, with submission deadline August 22. Topics include: Methods for effective, fair, and inclusive AI; Critiques of AI on the exclusion of identities; Methods for detecting and controlling bias; Perspectivist approaches to AI. Submission types: Long papers (8 pages), Short papers (4 pages), Extended abstracts, Mixed-media submissions (videos, blogs, codebase, artworks). For details, visit: identity-aware-ai.github.io

153

Reposted by Trustworthy AI Lab

UKP Lab @ukplab.bsky.social · 08/07/2025

🎙𝗚𝘂𝗲𝘀𝘁 𝗧𝗮𝗹𝗸 𝗯𝘆 𝗔𝗻𝗻𝗲 𝗟𝗮𝘂𝘀𝗰𝗵𝗲𝗿 𝗮𝘁 𝗨𝗞𝗣 𝗟𝗮𝗯 This Friday, we had the pleasure of hosting @a-lauscher.bsky.social, Associate Professor of @ds-hamburg.bsky.social, for a guest talk at the @ukplab.bsky.social.

131

Trustworthy AI Lab @tai-lab.bsky.social · 11/07/2025

Our group is launching a monthly seminar series! Next week, we will have @mhedderich.bsky.social from LMU Munich, who will give a talk at our seminar. Date: July 16 Time: 10.00 - 11.30 am CET You can either attend the seminar via Zoom or in-person. Register here if you are interested.

docs.google.com

University of Hamburg Data Science Group Seminar

This is the signup form for University of Hamburg Group Seminar. Please fill your details in here. You will be sent the zoom link a few hours before the lecture, if your details are valid. Details fo...

020

Trustworthy AI Lab @tai-lab.bsky.social · 23/06/2025

Big congratulations to all our talented researchers and collaborators who made this possible including @carolin-holtermann.bsky.social, @a-lauscher.bsky.social, @floschne-nlp.bsky.social, @paul-rottger.bsky.social, @sukannya.bsky.social and many more! See you all in Vienna.

020

Trustworthy AI Lab @tai-lab.bsky.social · 23/06/2025

🧵Excited to share that Data Science Lab Hamburg will be presenting 6 papers at #ACL2025 in Vienna! 🇦🇹 Our team has been working on cutting-edge research in multilingual AI, peer review analysis, and combating online harms. Here's what we're bringing to the conference 👇

Main Conference Papers:

Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model (authors: G Geigle, F Schneider, C Holtermann, C Biemann, R Timofte, A Lauscher and G Glavas)
LazyReview: A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews (authors: S Purkayastha, Z Li, A Lauscher, L Qu and I Gurevych)
Around the World in 24 Hours: Probing LLM Knowledge of Time and Place (authors: C Holtermann, P Röttger and A Lauscher)

Findings Papers:

GIMMICK: Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarking (authors: F Schneider, C Holtermann, C Biemann and A Lauscher)
FineCite: A Novel Approach For Fine-Grained Citation Context Analysis (authors: L Jantsch, D Koh, S Yoon, J Lee, A Lauscher and Y Suh)

Workshop on Online Abuse and Harms (WOAH):

Debunking with Dialogue? Exploring AI-Generated Counterspeech to Challenge Conspiracy Theories (authors: M Lisker, C Gottschalk, H Mihaljević)

272

Trustworthy AI Lab @tai-lab.bsky.social · 30/05/2025

Check out our new project using AI to revolutionize X-ray laser operations, featuring our PhD student Afshin Karimi. We're developing LLMs that analyze technical docs and control data to help operators troubleshoot complex synchrotron and XFEL systems, reducing costly downtime.

bwl.uni-hamburg.de

New research project to optimize laser operations

Faculties

020

Trustworthy AI Lab @tai-lab.bsky.social · 26/05/2025

We recently hosted @mxij.me from the IT University of Copenhagen's NLPnorth Lab for our speaker series. He presented a talk titled 'How Language Model Learning Dynamics Shape Social Inclusion.'

A photo of max pointing towards the screen

150

Reposted by Trustworthy AI Lab

Anne Lauscher @a-lauscher.bsky.social · 16/05/2025

If you are interested in the relationship between what is happening INSIDE 🔍 of our models 🤖 and OUTSIDE 🏞️ of our models 🤖, consider submitting to our workshop at COLM. #LLM #NLProc

082