IAugenstein Profile Banner
Isabelle Augenstein Profile
Isabelle Augenstein

@IAugenstein

Followers
12K
Following
5K
Media
215
Statuses
3K

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

Copenhagen, Denmark
Joined February 2012
Don't wanna be here? Send us removal request.
@IAugenstein
Isabelle Augenstein
2 months
๐Ÿ“ฃ 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: https://t.co/rxkZVEP6fs #NLProc #XAI @atanasovapepa @CopeNLU @AiCentreDK @DIKU_Institut
2
30
179
@IAugenstein
Isabelle Augenstein
2 days
Back after a successful #EMNLP2025 conference in Suzhou, China -- some impressions โคต๏ธ Our papers: https://t.co/72zhG7lwjB @atanasovapepa @rnav_arora @_kire_kara_ @Shoejoe_ @dustin_wright37 @JingyiSun_ @CopeNLU #NLProc
0
2
13
@_kire_kara_
Erik Arakelyan
3 days
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: https://t.co/blGtn8T4ta Work done with the amazing @PMinervini @PSH_Lewis @pat_verga @IAugenstein
@_kire_kara_
Erik Arakelyan
3 months
Our method for achieving more faithful, verifiable and robust #LLM reasoning (FLARE ๐Ÿ’ซ) has been accepted at #EMNLP2025 @emnlpmeeting ! Be sure to check out: https://t.co/cSHn97iLVJ Work done with the amazing @PMinervini @PSH_Lewis @pat_verga @IAugenstein
1
4
13
@IAugenstein
Isabelle Augenstein
8 days
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 โคต๏ธ #NLProc #XAI @SKMAINULISLAM11 @atanasovapepa
@SKMAINULISLAM11
Sekh (Sk) Mainul Islam
9 days
I am excited to share our new preprint answering this question: "Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement" ๐Ÿ“„ Paper: https://t.co/MYwnPRQ0eH ๐Ÿ’ป Code:
0
2
6
@CopeNLU
CopeNLU
10 days
Attending EMNLP 2025 in Suzhou, China this week? So is the CopeNLU group -- come find us at our paper presentations! โคต๏ธ https://t.co/3fdRaJjxSB @atanasovapepa @rnav_arora @whoSiddheshp, @_kire_kara_ @JingyiSun_ @Shoejoe_ @dustin_wright37 @lucasresck2 #NLProc #AI #EMNLP2025
0
3
14
@IAugenstein
Isabelle Augenstein
18 days
โฒ๏ธ ๐ŸŽ“ 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
@IAugenstein
Isabelle Augenstein
2 months
๐Ÿ“ฃ 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: https://t.co/rxkZVEP6fs #NLProc #XAI @atanasovapepa @CopeNLU @AiCentreDK @DIKU_Institut
0
6
11
@CopeNLU
CopeNLU
1 month
Which, whose, and how much knowledge do LLMs represent? We're excited to share our preprint answering these questions. ๐Ÿ“„Paper: https://t.co/amPblCS1zr ๐Ÿ’ปCode: https://t.co/6vef7LxJec @dustinbwright @_srishtiyadav @maria_antoniak @PeterEbertChri1 @IAugenstein @AiCentreDK 1/9
1
4
16
@IAugenstein
Isabelle Augenstein
1 month
Available #NLProc PhD positions: - Explainable NLU, start in Spring 2026 https://t.co/8ZnV6B4U1y - Trustworthy NLP, main supervisor: @atanasovapepa, start in Spring 2026 https://t.co/9xiEZByM56 - Open-topic: express interest via ELLIS, start in Autumn 2026
candidate.hr-manager.net
0
1
2
@IAugenstein
Isabelle Augenstein
1 month
Looking for PhD opportunites in #NLProc #XAI? We @copenlu @AiCentreDK @DIKU_Institut @atanasovapepa are hiring for a start in Spring or Autumn 2026. ๐Ÿ“† Application deadline: 31 October 2025 โ„น๏ธ Details: https://t.co/rxkZVEP6fs ๐Ÿ‘€ Reasons to apply:
Tweet card summary image
copenlu.com
The University of Copenhagen is a great place if you're both interested in high-quality NLP research and a high quality of life.
1
4
8
@atanasovapepa
Pepa Atanasova
2 months
๐ŸŽ“ Great opportunity for a fully funded PhD in Trustworthy NLP at the @DIKU_Institut & @AiCentreDK with @IAugenstein and me @CopeNLU! ๐Ÿ“… Application deadline: 30 October 2025 ๐Ÿ‘€ https://t.co/Ss2G9fdmHZ ๐Ÿ”— Apply here: https://t.co/wtOikqPC3k #NLProc #XAI #TrustworthyAI
0
2
8
@IAugenstein
Isabelle Augenstein
2 months
- Fully funded PhD fellowship on Explainable NLU: apply by 31 October 2025, start in Spring 2026: https://t.co/zCcfJSus5W - Open-topic PhD positions: express your interest through ELLIS by 31 October 2025, start in Autumn 2026: https://t.co/f63KBIZWY3 #NLProc #XAI
0
5
13
@_kire_kara_
Erik Arakelyan
3 months
Our method for achieving more faithful, verifiable and robust #LLM reasoning (FLARE ๐Ÿ’ซ) has been accepted at #EMNLP2025 @emnlpmeeting ! Be sure to check out: https://t.co/cSHn97iLVJ Work done with the amazing @PMinervini @PSH_Lewis @pat_verga @IAugenstein
Tweet card summary image
arxiv.org
Modern Question Answering (QA) and Reasoning approaches based on Large Language Models (LLMs) commonly use prompting techniques, such as Chain-of-Thought (CoT), assuming the resulting generation...
@_kire_kara_
Erik Arakelyan
1 year
๐Ÿ‘‹Psst! Want more faithful, verifiable and robust #LLM reasoning than with CoT, but using external solvers is meh? Our FLARE๐Ÿ’ซuses Logic Programming with Exhaustive Simulated Search to achieve this.๐Ÿงต With @PMinervini @PSH_Lewis @pat_verga @IAugenstein https://t.co/cSHn97iLVJ
0
7
28
@rnav_arora
Arnav Arora
3 months
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!
@rnav_arora
Arnav Arora
7 months
๐ŸšจNew pre-print ๐Ÿšจ 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: https://t.co/JqOfy0MzkL
2
2
21
@SKMAINULISLAM11
Sekh (Sk) Mainul Islam
3 months
๐Ÿš€ Excited to share our new preprint: BiasGym: Fantastic LLM Biases and How to Find (and Remove) Them ๐Ÿ“„ Read the paper: https://t.co/S0O5jaZbgQ
1
3
13
@hayu204
Haeun Yu
3 months
๐Ÿ™‹ How do Large Language Models internally process cultural knowledge? ๐ŸŒ Happy to share our new preprint "Entangled in Representations: Mechanistic Investigation of Cultural Biases in Large Language Models" ๐Ÿ“ƒ Paper: https://t.co/Gt14mjMiQg
3
28
202
@CopeNLU
CopeNLU
3 months
Thanks for everyone who came to our #acl2025nlp presentations (even the informal ones). Hope to connect again at #emnlp2025! #NLProc
@CopeNLU
CopeNLU
4 months
The CopeNLU group will be giving five paper presentations and one invited talk at #ACL2025NLP this week, on fact checking & cross-cultural #NLProc โคต๏ธ @atanasovapepa @rnav_arora @borenstein @IAugenstein @whoSiddheshp @gretawarren_ @saraveramarjano @HagstroemLovisa @hayu204
0
4
26
@ELLISforEurope
ELLIS
4 months
Meet @IAugenstein, Prof at @uni_copenhagen ๐Ÿ‡ฉ๐Ÿ‡ฐ, ELLIS Scholar, and member of @elliscph & ELLIS Program #NLProc. Her advice to young women in science: โ€œSuccess isn't just about tech skills. It's also about managing your career.โ€ #WomenInELLIS
0
3
13
@CopeNLU
CopeNLU
4 months
The CopeNLU group will be giving five paper presentations and one invited talk at #ACL2025NLP this week, on fact checking & cross-cultural #NLProc โคต๏ธ @atanasovapepa @rnav_arora @borenstein @IAugenstein @whoSiddheshp @gretawarren_ @saraveramarjano @HagstroemLovisa @hayu204
1
2
5
@IAugenstein
Isabelle Augenstein
4 months
And thanks again to all organisers and volunteers -- couldn't have done it without you ๐Ÿ˜Š @yoonnabc @whoSiddheshp @BarryNorton @atanasovapepa @dustin_wright37 @rnav_arora @BjorgMagnus
0
1
6
@IAugenstein
Isabelle Augenstein
4 months
Congrats to the best poster awardees! @a_jy_l Shared Global & Local Geometry of LMs: https://t.co/a7Rltcs9O1 @AntoniaKaramol Evaluating Multimodal LMs for Visual Impairment: https://t.co/SUlCPK8TD3 @gretawarren_ Can Community Notes Replace Fact-Checkers? https://t.co/teXGTLUmSg
1
1
5