(1) SPaRC: A Spatial Pathfinding Reasoning Challenge
by Lars Benedikt Kaesberg, Jan Philip Wahle, Terry Ruas, and Bela Gipp

TL;DR: SPaRC is a 2D pathfinding dataset that necessitates multi-step spatial and rule-based reasoning, underscoring a significant gap in spatial understanding between human and AI reasoning models.

Paper: https://aclanthology.org/2025.emnlp-main.526 or https://sparc.gipplab.org

Poster: https://www.slideshare.net/slideshow/emnlp-2025-poster-sparc-a-spatial-pathfinding-reasoning-challenge/284023981

Presentation: Wed. Nov. 5, 14:30-16:00, Hall C

(2) Contrastive Learning Using Graph Embeddings for Domain Adaptation of Language Models in the Process Industry
by Anastasia Zhukova*, Jonas Lührs*, Christian E. Lobmüller, and Bela Gipp (*equal contribution)

TL;DR: We explore the use of knowledge graphs for fine-tuning language models, specifically the text encoder, when the text domain data is low-resource.

Paper: https://aclanthology.org/2025.emnlp-industry.103/

Poster: https://www.slideshare.net/slideshow/contrastive-learning-using-graph-embeddings-for-domain-adaptation-of-language-models-in-the-process-industry/283913368

Presentation: Wed., Nov. 5, 14:30-16:00, Hall C, Industry Poster Session 1

(3) MALLM: Multi-Agent Large Language Models Framework
by Jonas Becker*, Lars Benedikt Kaesberg*, Niklas Bauer, Jan Philip Wahle, Terry Ruas, and Bela Gipp (*equal contribution)

TL;DR: A framework for multi-agent debate to conduct your research experiments. Evaluate agent personas, response generators, discussion paradigms, and decision protocols.

Paper: https://aclanthology.org/2025.emnlp-demos.29/ or https://mallm.gipplab.org

Poster: https://www.slideshare.net/slideshow/mallm-multi-agent-large-language-models-framework-emnlp-2025/284028707

Presentation: Thu., Nov. 6, 16:30-18:00, Hall C

(4) TrojanStego: Your Language Model can Secretly Be A Steganographic Privacy Leaking Agent
by Dominik Meier, Jan Philip Wähle, Paul Röttger, Terry Ruas, Bela Gipp

TL;DR: We explore a novel threat model where LLMs secretly embed information in their output.

Paper: https://aclanthology.org/2025.emnlp-main.1386/

Poster: https://pdfhost.io/v/WsBM3XwhdJ_TrojanStego-Dm-JW-2-1

Presentation: Fri., Nov. 7, 10:30-12:00, Hall C

(5) Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questions
by Frederic Kirstein, Sonu Kumar, Terry Ruas, Bela Gipp

TL;DR: We introduce FRAME, a fact-centric pipeline that incorporates statement–context tuples, along with SCOPE, a reason-out-loud personalization protocol, and P-MESA, a reader-aligned metric. We reframe summarization as enrichment, cutting hallucination/omission, and improving relevance, goal alignment, and knowledge fit in meeting summaries.

Paper: https://aclanthology.org/2025.findings-emnlp.1094/

Poster: https://de.slideshare.net/slideshow/emnlp25-poster/284036994

Presentation: Fri., Nov. 7, 12:30-13:30, Hall C

Der Beitrag GippLab Presents Five Papers at EMNLP Conference in China erschien zuerst auf Prof. Dr. Bela Gipp, University of Göttingen, GippLab.

• AI Methods
• Information Technologies | Industry Specific and Service Software

SAMI (Shiftconnector Artificial Manufacturing Intelligence) spans over three functions: SAMI Search, SAMI Solutions, and SAMI Chat. SAMI helps process manufacturers facilitate faster problem resolution and better informed decision-making. The awards recognize both research and technological achievement, but also user-centric design, thereby proving value in industrial operations. The collaboration project of the Plant Assistant is driven on the GippLab side by Anastasia Zhukova, Marco Kaiser, Finn Schmidt, and Dr. Christian Matt on the Eschbach side. This project is supported by the Federal Ministry for Economic Affairs and Climate Action (BMWK) under the ZIM program on the basis of a decision by the German Bundestag.

For more information about the German Innovation Award, please visit this page.

Der Beitrag Collaborative AI project with our industry partner eschbach wins twice in the German Innovation Award 2025 erschien zuerst auf Prof. Dr. Bela Gipp, University of Göttingen, GippLab.

Smart Solutions is an NLP-driven recommender system designed specifically for shift workers in the process industry. By analyzing historical shift records, it efficiently extracts, ranks, and summarizes documented solutions, providing operators with a comprehensive overview of available solutions in seconds. This capability accelerates troubleshooting and significantly reduces production downtimes.

Please visit the project page for more information about our ongoing research collaboration with eschbach.

Der Beitrag “Smart Solutions” wins Best of Industry Award 2024 erschien zuerst auf Prof. Dr. Bela Gipp, University of Göttingen, GippLab.

The newly funded project aims to develop advanced AI-driven multilingual search and recommendation algorithms tailored to handle the process industry’s unique terminology and language conventions. The enhanced AI capabilities will significantly elevate the Smart Search functionality of eschbach’s flagship product, Shiftconnector, by enabling seamless searches and recommendations across multiple languages. This innovation is particularly vital for global organizations utilizing Shiftconnector in production facilities worldwide.

eschbach and GippLab have collaborated successfully on research and development projects since 2015. Our joint efforts won multiple prestigious awards for product improvements and benefited the research community. This newly secured grant will mark a new chapter in our collaboration, supporting critical research, data science, and software development roles at both eschbach and GippLab.

Please visit this page to learn more about our fruitful research collaboration with eschbach.

Der Beitrag Federal Funding Approved for AI Research Collaboration with eschbach erschien zuerst auf Prof. Dr. Bela Gipp, University of Göttingen, GippLab.

Smart Search is integrated into Shiftconnector—eschbach’s enterprise software platform for process manufacturing. The feature provides users with powerful and user-friendly search capabilities for explicit information and implicit knowledge on plant operations across Shiftconnector’s vast data collection.

Our group, notably Prof. Bela Gipp and Anastasia Zhukova, collaborated with eschbach and one of its major customers on developing Smart Search by contributing research expertise in Natural Language Processing.

The current award is already the second recognition of the Smart Search functionality, which also won the Game Changer Award in June.

The research is funded by ZIM (Zentrales Innovationsprogramm Mittelstand) run by the German Ministry of Economic Affairs and Climate Action.

More information on:

• Our collaboration with eschbach
• The Best of Industry Award
• The Game Changer Award

Der Beitrag Collaborative AI project with our industry partner eschbach wins Best of Industry Award erschien zuerst auf Prof. Dr. Bela Gipp, University of Göttingen, GippLab.