Lightnews — Scholar-powered news

NLPnorth

@nlpnorth.bsky.social

290 followers 260 following 24 posts

#NLProc research group @itu.dk (Copenhagen, Denmark) 🔗 nlpnorth.github.io

Posts Media Videos Starter Packs

NLPnorth @nlpnorth.bsky.social · 29d

Have you recently used a crowdsourcing platform to collect data or annotations?
We are running a study about the use of LLMs in crowdsourcing platforms. If you want to help, fill in this 10 min survey 👉https://tinyurl.com/39ab55wf

#NLProc

Amelie Wuehrl @nlp-amelie.bsky.social · Sep 5

Crowdsourcing datasets is very common, but how much of those results come from LLMs these days? How can we prevent it? Much of it is unclear. This is why we’re conducing a survey (~10 min) to gather community experiences, challenges, and solutions.
Share your thoughts 👉https://tinyurl.com/39ab55wf

Qualtrics Survey | Qualtrics Experience Management

The most powerful, simple and trusted way to gather experience data. Start your journey to experience management and try a free account today.

ugent.qualtrics.com

NLPnorth @nlpnorth.bsky.social · Jul 30

Big congrats to our postdoc @elisabassignana.bsky.social for the well deserved Social Impact award at #ACL2025NLP!!

Elisa Bassignana @elisabassignana.bsky.social · Jul 30

Super proud to receive the Social Impact award at #ACL2025NLP for our paper together with @amandacurry.bsky.social (eq contribution) and @dirkhovy.bsky.social 🎉

#NLProc

NLPnorth @nlpnorth.bsky.social · Jul 30

Having a great time at #ACL2025NLP!

#NLProc

NLPnorth @nlpnorth.bsky.social · Jul 22

📄The AI Gap: How Socioeconomic Status Affects Language Technology Interactions
👥 @elisabassignana.bsky.social @amandacurry.bsky.social @dirkhovy.bsky.social
🔗 arxiv.org/pdf/2505.12158
🎯We call for inclusive NLP technologies to accommodate different SES and mitigate the digital divide.

NLPnorth @nlpnorth.bsky.social · Jul 22

📄 DECAF: A Dynamically Extensible Corpus Analysis Framework
👥 @mxij.me Rob van der Goot @annarogers.bsky.social
🔗 mxij.me/x/decaf
🎯 DECAF supports generalization research with clear train/test separation at scale.

NLPnorth @nlpnorth.bsky.social · Jul 22

📄Identifying Open Challenges in Language Identification
👥 Rob van der Goot
🎯 We identify and quantify a variety of remaining challenges for language classification and identify cross-domain evaluation as a main bottleneck, where n-gram based models outperform transformer-based LMs.

NLPnorth @nlpnorth.bsky.social · Jul 22

📄 Research Community Perspectives on ‘Intelligence’ and LLMs
👥 @brtrm.bsky.social @terne.bsky.social @annarogers.bsky.social @heinrichst.bsky.social
🔗 arxiv.org/abs/2505.20959
🎯 What do we mean when we talk about LLM 'intelligence'? Top criteria are generalization, adaptability & reasoning.

NLPnorth @nlpnorth.bsky.social · Jul 22

📄 Hypernetworks for Personalizing ASR to Atypical Speech
👥 @mxij.me *, Dianna Yee*, Karren Yang, Gautam Varma Mantena, Colin Lea
🔗 doi.org/10.1162/tacl...
🎯 Using hypernetworks, we enable ASR for atypical speech via a mix of dynamic personalization and targeted adaptation sharing.

NLPnorth @nlpnorth.bsky.social · Jul 22

📣 Next week we will be in Vienna for @aclmeeting.bsky.social to present a couple of works from our lab!

Find more about each of them below 🧵👇

#NLP #NLProc #ACL2025NLP @itu.dk @aicentre.dk

NLPnorth @nlpnorth.bsky.social · Jul 21

Rob and @mjjzha.bsky.social (AAU) recently participated in the TalentCLEF shared task on job title and skill matching. They show that prompting performs well for job titles, but encoder models still prevail for skill matching.

📄 arxiv.org/pdf/2506.19058

#NLProc #NLP

Reposted by NLPnorth

Anna Rogers @annarogers.bsky.social · Jun 2

🤯 We use the term 'intelligence' a lot, but wth do we mean?

We got 303 survey responses from researchers. The most agreed-on criteria are generalization, adaptability & reasoning.

ACL Findings preprint: arxiv.org/abs/2505.20959
with @brtrm.bsky.social @terne.bsky.social @heinrichst.bsky.social /1

Reposted by NLPnorth

Beatrice Savoldi @bsavoldi.bsky.social · Jun 3

🔍 Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio!

👉 bit.ly/sondaggio_ai...

(è anonimo, richiede ~10 minuti, e se partecipi o lo fai girare ci aiuti un sacco🙏)

Ci interessa anche raggiungere persone che non si occupano e non sono esperte di AI!

Qualtrics Survey | Qualtrics Experience Management

The most powerful, simple and trusted way to gather experience data. Start your journey to experience management and try a free account today.

NLPnorth @nlpnorth.bsky.social · May 30

📢 New #ACL2025 Findings preprint from @brtrm.bsky.social about the perspectives on 'intelligence' in the research community!

A survey of 300+ researchers shows that most don’t view current NLP systems as intelligent and only few see building intelligent systems as a research goal.

#NLProc @itu.dk

Bertram Højer @brtrm.bsky.social · May 30

Our survey paper "Research Community Perspectives on 'Intelligence' and Large Language Models" has been accepted to the ACL Findings 2025 - and I'll be in Vienna to present the work in July!

arxiv.org/abs/2505.20959

Research Community Perspectives on "Intelligence" and Large Language Models

Despite the widespread use of ''artificial intelligence'' (AI) framing in Natural Language Processing (NLP) research, it is not clear what researchers mean by ''intelligence''. To that end, we present...

NLPnorth @nlpnorth.bsky.social · May 26

📢 New #ACL2025 preprint by our postdoc @elisabassignana.bsky.social about the impact of socioeconomic status (SES) on the adoption and usage of language technologies!

A first step for better understanding the AI Gap across SES and develop more inclusive language technologies ⚖️🤖

#NLProc @itu.dk

Elisa Bassignana @elisabassignana.bsky.social · May 26

🚨 New paper accepted at #ACL2025 Main conference! 🙌
"The AI Gap: How Socioeconomic Status Affects Language Technology Interactions"
w/ @amandacurry.bsky.social & @dirkhovy.bsky.social

Very happy for this first collab with @milanlp.bsky.social 🤝

🔗 lnkd.in/dtsH3gaX
🤗 lnkd.in/d7diuBJh

🧵👇
#ACL2025

Reposted by NLPnorth

Anna Rogers @annarogers.bsky.social · May 26

📢 The Copenhagen NLP Symposium on June 20th!

- Invited talks by @loubnabnl.hf.co (HF) @mziizm.bsky.social (Cohere) @najoung.bsky.social (BU) @kylelo.bsky.social (AI2) Yohei Oseki (UTokyo)
- Exciting posters by other participants

Register to attend and/or present your poster at cphnlp.github.io /1

Copenhagen NLP Symposium 2025

symposium website

cphnlp.github.io

NLPnorth @nlpnorth.bsky.social · Apr 30

Last week, our PhD student @brtrm.bsky.social presented "Improving Reasoning Performance in Large Language Models via Representation Engineering" at ICLR 2025 🤖💭

If you missed his presentation, check out the paper here arxiv.org/abs/2504.19483

#NLProc #ICLR2025

NLPnorth @nlpnorth.bsky.social · Apr 29

Welcome to the team Amelie! We are very happy to have you with us 🥳🇩🇰

Amelie Wuehrl @nlp-amelie.bsky.social · Apr 29

I've turned the page to a new academic chapter & started a postdoc position @itu.dk in Copenhagen 🎉 I'll be working with @annarogers.bsky.social in the PlagAIrism project, where we develop methods to identify & cite sources in LLM training data that contributed to a generated text.

NLPnorth @nlpnorth.bsky.social · Mar 2

📄 Efficient Elicitation of Fictitious Nursing Notes from Volunteer Healthcare Professionals
👥 Jesper Bornerup @chrha.bsky.social
🎯 We introduce a data collection method and Danish dataset of fictitious nursing notes by prompting volunteers with situations
🗓 March 3rd, 14.10 (Poster session)

NLPnorth @nlpnorth.bsky.social · Mar 2

📄 DAKULTUR: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers
👥 @mxijme.bsky.social @mjjzha.bsky.social @elisabassignana.bsky.social
Peter Trolle, Rob van der Goot
🎯 A user study for analyzing the cultural awareness of LLMs in Danish
🗓 March 2nd, 10:30 (NB-REAL)

NLPnorth @nlpnorth.bsky.social · Mar 2

📄 MORSED: Morphological Segmentation of Danish and its Effect on Language Modeling
👥 Rob, Anette, Emil, Mikkel, Nicolaj, @mjjzha.bsky.social @elisabassignana.bsky.social
🎯 We create morphological segmenters for Danish and using them for LM training
🗓 March 3rd, 14.10 (Poster session)

NLPnorth @nlpnorth.bsky.social · Mar 2

📄SnakModel: Lessons Learned from Training an Open Danish Large Language Model
👥 @mjjzha.bsky.social @mxijme.bsky.social @elisabassignana.bsky.social Rob
🔗 shorturl.at/4PjoQ
🎯Snakmodel is an LLM continuously pre-trained on 13.6B Danish tokens and 3.7M instruction pairs
🗓March 3rd, 10.45 (Ida-Euroopa)

NLPnorth @nlpnorth.bsky.social · Mar 2

📣 @nodalida.bsky.social 🇪🇪 is starting soon and we will be presenting a couple of papers in the next days.

Find more about each of them in the 🧵

#NLP #NLProc

NLPnorth @nlpnorth.bsky.social · Feb 7

Exciting job opportunity in collaboration with our group!

#NLProc

👇👇👇

Christian Hardmeier @chrha.bsky.social · Feb 7

We have a two year full-time position suitable for a postdoc with experience in NLP and a passion for mental health applications in an exciting collaborative project on analysing psychotherapy with NLP methods. Is this for you? Knowledge of Danish required. candidate.hr-manager.net/ApplicationI...

Data Scientist for pioneering research combining AI and psychotherapy

Are you passionate about the intersection of AI and mental health? Join the ALF project at VIRTU Research Group in a 2-year, full-time position, where you will

candidate.hr-manager.net

NLPnorth @nlpnorth.bsky.social · Dec 19

Nice to see @mjjzha.bsky.social presenting our joint collaboration with Aallborg University: SnakModel, a new language model for Danish 🇩🇰
(w/ @mxijme.bsky.social @elisabassignana.bsky.social and Rob van der Goot)

Dennis Ulmer @dnnslmr.bsky.social · Dec 19

Very happy to have learned about my old @nlpnorth.bsky.social colleague @mjjzha.bsky.social et al.'s work on SnakModel, a new language model for Danish!

Picture of Mike Zhang presenting his work on a Danish language model called SnakModel.

NLPnorth @nlpnorth.bsky.social · Dec 18

Congratulations to Dr. Marija Stepanović for defending her thesis "Phonetic Vowel Representation for Cross-Lingual Automatic Speech Recognition"! Well deserved 🎓🎉