We’re proud to announce that ACL 2025 awarded our group members “Best Resource Paper” award and “Best SemEval Task” award for their work on multilingual resources 🎉👏. More details: . #ACL2025 #ACL25.#ACL2025NLP

You need to MIMIC to get FAME: Solving Meeting Transcript Scarcity with Multi-Agent Conversations. Authors: Frederic Kirstein, Muneeb Khan, Jan Philip Wahle, Terry Ruas, and Bela Gipp. 📄 Preprint:

Join millions who have switched to Grok.

Voting or Consensus? Decision-Making in Multi-Agent Debate . Authors: Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle, Terry Ruas, and Bela Gipp. 📄 Preprint:

BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages. Authors: Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin, Jan Philip Wahle, Terry Ruas, Meriem Beloucif, et al. 📄 Preprint:

GippLab attending #ACL2025NLP in Vienna this week!. 📄 We presented three papers 🙌. 🔗 Find the titles and links to all papers in the comments below👇 . #ACL #ACL2025 #ACL25

GippLab presenting the FPV Quadcopter Seminar and their AI-assisted drones at the @unigoettingen “Nacht des Wissens”. @ndw_goe. Come visit our stand in the Alfred-Hessel-Saal and try piloting a drone yourself! 😉 @subgoettingen. #NachtDesWissens #Goettingen #FPVDrones #ndwgoe

GippLab is presenting our research at the 31st International Conference on Computational Linguistics this week. Thanks for the great discussions so far! 👏 . #COLING2025

5️⃣  "Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language".🖋️ Anastasia Zhukova et al. ☑️ LoResLM Workshop. 🔗

4️⃣ "Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator".🖋️ Frederic Kirstein et al. ☑️ Industry track. 🔗

3️⃣ "Citation Amnesia: On The Recency Bias of Natural Language Processing and Other Academic Fields".🖋️ Jan Philip Wahle et al. ☑️ Main track. 🔗

2️⃣ "What's Wrong? Refining Meeting Summaries with LLM Feedback".🖋️ Frederic Kirstein et al. ☑️ Main track. 🔗

1️⃣  "Towards Human Understanding of Paraphrase Types in Language Models".🖋️ Dominik Meier et al. ☑️ Main track. 🔗

GippLab is excited to share that our group has five accepted papers at #COLING2025! 🎉 . 🧵 Expand this thread to see our contributions with links to the full text papers 📄. See you at the conference!. #ComputationalLinguistics .#NLProc #NLP.

The paper summarized in poster form:

A very engaging poster session at #EMNLP2024 this morning! The room was packed!. Find the full paper that @jpwahle and @ruasterry presented here: . 📄

RT @jpwahle: Are you interested in LLM sensitivity, model robustness, and paraphrases?. Stop by at our #EMNLP paper today, Wednesday at 10:….

GippLab goes #EMNLP2024 🙌. 🔗 to our conference papers:. 📄 What’s under the hood: Investigating Automatic Metrics on Meeting Summarization: 📄 Paraphrase Types Elicit Prompt Engineering Capabilities:

Wir suchen eine Assistenz für unser Team an der @uniGoettingen und @subugoe! Wir bieten ein modernes Arbeitsumfeld mit viel Gestaltungsspielraum, flache Hierarchien und eine unbefristete Anstellung im öffentlichen Dienst. Jetzt bis 28.4. bewerben:

RT @zbMATH: It was a great pleasure to host the doctoral workshop of @GippLab and the @FIZKarlsruhe Mathematics Information Research Group!….

The podcast of Faktor Magazine released an episode with @BelaGipp on the opportunities and threats of AI, specifically of AI-generated text, in the context of academic research and education. 🎧 Listen on Spotify. #KIForschung #GPT #ChatGPT #AI.