Isabelle Augenstein

3.1K posts

Isabelle Augenstein banner
Isabelle Augenstein

Isabelle Augenstein

@IAugenstein

Full Professor @CopeNLU @uni_copenhagen. Formerly @ucl_nlp, @SheffieldNLP. Explainable AI, Natural Language Processing, ML.

Copenhagen, Denmark Katılım Şubat 2012
1.1K Takip Edilen11.9K Takipçiler
Isabelle Augenstein
Isabelle Augenstein@IAugenstein·
Just under two weeks to go to apply to join our @CopeNLU lab as a PhD student or postdoc! ⤵️ #academicjobs #NLProc #XAI #HCI @AiCentreDK @DIKU_Institut
Isabelle Augenstein@IAugenstein

📢 PhD & postdoc call for start in autumn 2026 📢 Join a new interdisciplinary project on Human-Centered Explainable LLMs led by @quillis & me @CopeNLU @AiCentreDK ⏳ 1 Feb 2026 ℹ️ copenlu.com/news/funded-ph… 🗒️ employment.ku.dk/phd/?show=1532… (PhD); employment.ku.dk/faculty/?show=… (Postdoc)

English
2
2
14
2.8K
Isabelle Augenstein retweetledi
CopeNLU
CopeNLU@CopeNLU·
CopeNLU had a blast attending @EurIPSConflast last week -- thanks so much to the organisers (Søren Hauberg, @SergeBelongie, @bschoelkopf, Aasa Feragen) for putting this together! Non-scientific highlights were clearly the banquet dinner & the specially brewed EurIPA.
CopeNLU tweet media
English
0
3
7
781
Isabelle Augenstein retweetledi
Erik Arakelyan
Erik Arakelyan@_kire_kara_·
Had an great time presenting our work on Faithful and Verifiable #LLM reasoning at @emnlpmeeting and catching up with all the amazing researchers. Be sure to check out: arxiv.org/abs/2410.11900 Work done with the amazing @PMinervini @PSH_Lewis @pat_verga @IAugenstein
Erik Arakelyan tweet media
Erik Arakelyan@_kire_kara_

Our method for achieving more faithful, verifiable and robust #LLM reasoning (FLARE 💫) has been accepted at #EMNLP2025 @emnlpmeeting ! Be sure to check out: arxiv.org/abs/2410.11900 Work done with the amazing @PMinervini @PSH_Lewis @pat_verga @IAugenstein

English
1
4
15
3.3K
Isabelle Augenstein
Isabelle Augenstein@IAugenstein·
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 @SKMAINULISLAM11 @atanasovapepa
Sekh (Sk) Mainul Islam@SKMAINULISLAM11

I am excited to share our new preprint answering this question: "Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement" 📄 Paper: arxiv.org/pdf/2511.01706 💻 Code: github.com/copenlu/pk-ck-…

English
0
2
7
2K
Isabelle Augenstein
Isabelle Augenstein@IAugenstein·
⏲️ 🎓 Only a few days left to apply to do a PhD in Natural Language Processing with @atanasovapepa and me @CopeNLU @AiCentreDK @DIKU_Institut #NLProc #ML #XAI #phdpositions #academicjobs
Isabelle Augenstein@IAugenstein

📣 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: copenlu.com/news/phd-fello… #NLProc #XAI @atanasovapepa @CopeNLU @AiCentreDK @DIKU_Institut

English
0
6
11
2.1K
Isabelle Augenstein retweetledi
Erik Arakelyan
Erik Arakelyan@_kire_kara_·
Our method for achieving more faithful, verifiable and robust #LLM reasoning (FLARE 💫) has been accepted at #EMNLP2025 @emnlpmeeting ! Be sure to check out: arxiv.org/abs/2410.11900 Work done with the amazing @PMinervini @PSH_Lewis @pat_verga @IAugenstein
Erik Arakelyan@_kire_kara_

👋Psst! Want more faithful, verifiable and robust #LLM reasoning than with CoT, but using external solvers is meh? Our FLARE💫uses Logic Programming with Exhaustive Simulated Search to achieve this.🧵 With @PMinervini @PSH_Lewis @pat_verga @IAugenstein arxiv.org/abs/2410.11900

English
0
7
29
6.3K
Isabelle Augenstein retweetledi
Arnav Arora
Arnav Arora@rnav_arora·
Happy to share that our work on multi-modal framing analysis of news articles was accepted to #EMNLP2025! Understanding news 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!
Arnav Arora@rnav_arora

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

English
2
2
22
1.9K
Isabelle Augenstein retweetledi
Sekh (Sk) Mainul Islam
Sekh (Sk) Mainul Islam@SKMAINULISLAM11·
🚀 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
Sekh (Sk) Mainul Islam tweet media
English
1
3
14
1.5K
Isabelle Augenstein retweetledi
Haeun Yu
Haeun Yu@hayu204·
🙋 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
Haeun Yu tweet media
English
3
28
203
15.6K
Isabelle Augenstein retweetledi
CopeNLU
CopeNLU@CopeNLU·
Thanks for everyone who came to our #acl2025nlp presentations (even the informal ones). Hope to connect again at #emnlp2025! #NLProc
CopeNLU tweet mediaCopeNLU tweet mediaCopeNLU tweet mediaCopeNLU tweet media
CopeNLU@CopeNLU

The CopeNLU group will be giving five paper presentations and one invited talk at #ACL2025NLP this week, on fact checking & cross-cultural #NLProc ⤵️ @atanasovapepa @rnav_arora @borenstein @IAugenstein @whoSiddheshp @gretawarren_ @saraveramarjano @HagstroemLovisa @hayu204

English
0
4
26
6.7K
Isabelle Augenstein retweetledi
ELLIS
ELLIS@ELLISforEurope·
Meet @IAugenstein, Prof at @uni_copenhagen 🇩🇰, ELLIS Scholar, and member of @elliscph & 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
English
0
2
13
1.5K

Keşfet

@CopeNLU @AiCentreDK @DIKU_Institut @SergeBelongie @bschoelkopf @quillis @atanasovapepa @rnav_arora