
Natural Language Learning & Generation @utn_nuremberg We do exist & we grow! Text generation, Evaluation, Digital Humanities, Social Science #NLProc #NLP
Nürnberg, Bayern
Joined December 2022
- Tweets108
- Following116
- Followers132
- Likes339
Christian Greisinger will present "Tikzilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning" (openreview.net/forum?id=rJv2…) today 10:30 AM-1:00pm. Pavilion 4 P4 #3301 @iclr_conf #ICLR2026
Say hello to him and learn about text-to-tikz generation for science!
📢📢We have two postdoc positions, 12-15 months.
P1: Open position on the research topics of the group (evaluation, interdisciplinary with humanities+social sciences, AI4Science).
P2: LLM-based authorship verificiation.
Deadline: 20.02.2026
Link: utn.de/en/career/job-opening…
NLLG retweeted
🥳Our 1st Workshop on Human-Centric LLMs for Science still welcomes non-archival submissions until November 14.
Details are at sciprodllm.github.io/2025/cf…
We have a great lineup of invited speakers: @gneubig, @annargrs, @RobertTLange, @mbodhisattwa
Tomorrw, Yanran Chen @ccccahhh and Ran Zhang @yyrrss2021 will present their #EMNLP2025 papers on "Argument summarization & evaluation in the era of LLMs" and "LiTransProQA: LLM-based Literary Translation evaluation metric with Professional QA". Hall C3, 14-15:30 (posters)
NLLG retweeted
📢📢 This year Eval4NLP is co-located with #aacl2025. Our CFP is now out: eval4nlp.github.io/2025/cfp.…
Paper submission deadline: September 29, 2025. Direct submission via OpenReview.
ARR commitment deadline: October 27, 2025
Notification of acceptance: November 3, 2025
Two more days left to apply 👇👇
xitter.cf/NLLG_lab/status/192819…
📢📢👇New job openings. Topic: social bias detection+analysis with LLMs across time (1950-now) & languages. There are 2 Post-Doc/PhD positions, supervised by @egere14 (@utn_nuremberg)+Simone Ponzetto (@dwsunima). Fully funded, up to 3 yrs.
More infos: nl2g.github.io/positions
📢📢👇New job openings. Topic: social bias detection+analysis with LLMs across time (1950-now) & languages. There are 2 Post-Doc/PhD positions, supervised by @egere14 (@utn_nuremberg)+Simone Ponzetto (@dwsunima). Fully funded, up to 3 yrs.
More infos: nl2g.github.io/positions
NLLG retweeted
‼️Call for Participation: IT:U Summer School 2025 on Natural Language Processing‼️
We are excited to announce that the IT:U Summer School 2025, focused on NLP, will take place on July 25–26 in Linz, Austria, just ahead of #ACL2025.
🔗 Register here: it-u.at/en/itu-summer-school…
NLLG retweeted
👉 slator.ch/QAEvaluationLitera…
A new #LLM-based metric builds on the promise of question-answering ⁉️ to evaluate 🔍 literary translations, capturing ✨ style, 🎶 tone, and cultural 🌏 nuance.
#translation #xl8 #t9n #AI @andyweizhao @egere14 @aberdeenuni @utn_nuremberg @NLLG_lab
NLLG retweeted
Prof. Steffen Eger (@egere14) from UTN gave a fantastic talk on "Literary Translation in the Era of LLMs" at our NLP group seminar ✏️📖
NLLG retweeted
We're delighted to host @egere14 for an insightful talk on "Multimodal Scientific Content Generation with LLMs", covering tools like AutomaTikz, DeTikZify, and ScImage that aim to automate and enhance scientific figure generation🤖📚
How nice 🥳🎉 - we got an outstanding paper at #naacl2025 with our paper on literary translation (evaluation) with LLMs aclanthology.org/2025.naacl-…. Congrats to @yyrrss2021 @andyweizhao @egere14
Literary translation (and its evaluation) with LLMs is an important—and ethically sensitive—MT use case that's recently gained momentum across disciplines. Grateful that #NLProc community (and #NAACL2025) is recognizing our work!
NLLG retweeted
I'm at NAACL 2025, presenting my work on prompt optimization for MT evaluation with LLMs. Come say hi at board 50 at 11:00-12:30, Hall 3.
📢📢 Our new preprint on generating scientific figures with less/no aligned data is out. Joint work with @EddyIlg @margret_keuper, @prajdabre1, @egere14 (and a few more). 👇
xitter.cf/jbelouadi/status/19026…
🔥 New preprint out! Our model, TikZero, generates scientific figures from text captions as high-level, human-interpretable, and editable graphics programs, outperforming traditional, end-to-end trained models. (1/3)
#TikZero #GenerativeAI #MachineLearning
























