NLLG

📢📢 This year Eval4NLP is co-located with #aacl2025. Our CFP is now out: eval4nlp.github.io/2025/cfp.html 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 👇👇 x.com/NLLG_lab/statu…

📢📢👇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

‼️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-…

👉 slator.ch/QAEvaluationLi… 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

Prof. Steffen Eger (@egere14) from UTN gave a fantastic talk on "Literary Translation in the Era of LLMs" at our NLP group seminar ✏️📖

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🤖📚

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). 👇 x.com/jbelouadi/stat…

Thanks for the chance to discuss some findings and thoughts on evaluation at @NLLG_lab's retreat with @egere14 's group & friends. ✍️Even the evaluation of basic classification tasks can lack clarity (for various reasons); important challenges unsolved! #datascience Pointers👇

The AI race is just beginning. Building on the European AI Champions initiative, I’m glad to announce InvestAI 🇪🇺 We aim to mobilise €200 billion in AI investments in Europe ↓

Transforming Science with LLMs A comprehensive survey on AI-assisted scientific discovery, experimentation, content generation, and evaluation.

PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics Evaluating machine-generated language with large models like GPT-4 is expensive due to high token usage. This work introduces a method that uses a smaller fine-tuned model to compress input data,…