DICE Research Group

🎉 𝗡𝗲𝘄 𝗣𝗮𝗽𝗲𝗿 𝗮𝗰𝗰𝗲𝗽𝘁𝗲𝗱! “Rethinking Explanations: Formalizing Contrast in Description Logics” by @Yaa_Siir, Arnab Sharma, @NgongaAxel & Balram Tiwari has been accepted at #XAI2026 in Fortaleza, Brazil 🇧🇷. 🔗 xaiworldconference.com/2026/ Congrats to the authors! 👏

🚀Kick-off of the 2nd funding phase of TRR 318 “Constructing Explainability”! DICE contributes to two subprojects: 👉INF – building a data & information management infrastructure with RAG-based QA 👉C07 – interactive, dialogue-based explanations with LLMs.

📈 DICE Embeddings: New KGE models, ensemble & weight-averaging strategies, improved evaluation workflows, tutorials, and bug fixes. 👉github.com/dice-group/dic… ⚠️ Minimum Python version is now 3.11 for all three libraries. (3/3)

🧠 Ontolearn: Refactored concept & neural learners, improved triple store, and new SAT-based learners.👉github.com/dice-group/Ont… 🧩 OWLAPy: Introducing AGen-KG, a scalable agentic KG generation model from text with prompt-based customization. 👉 github.com/dice-group/owl… (2/3)

🚀 𝗡𝗲𝘄 𝗥𝗲𝗹𝗲𝗮𝘀𝗲𝘀: 𝗢𝗻𝘁𝗼𝗹𝗲𝗮𝗿𝗻, 𝗢𝗪𝗟𝗔𝗣𝗬 & 𝗗𝗜𝗖𝗘 𝗘𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀 We’ve released new versions across our neuro-symbolic AI tools, bringing new features, performance improvements, and important updates.👇 (1/3)

Yesterday, we hosted the HNI Forum 2026 at the Heinz Nixdorf Institute. 👉Prof. Hector Geffner (RWTH Aachen) on "Representation learning to act and plan" 👉 Prof. Axel Ngonga on “Explainable neurosymbolic machine learning on knowledge graphs” Thanks to all who joined! 🙌

👉"Discrete Diffusion-Based Model-Level Explanation of Heterogeneous GNNs with Node Features" by P. Das & S. Heindorf. 👏 Congratulations to all authors! (2/2)

🚀 We’re excited to announce two paper acceptances @TheWebConf (#TheWebConf2026), taking place April 13–17 in Dubai 👉"A Simplex Approach to Synthetic Knowledge Graph Generation" by A. Silva, A. Bhopalsing Pundir, M. Röder & @NgongaAxel. (1/2)

🎙️ New podcast episode (in German): Kernel und Kernobst #073 “Does AI Always Have to Be Friendly?” @NgongaAxel was a guest and discussed everyday questions about AI, taking a deeper, more academic look at how AI works. 👉trommelspeicher.de/podcast/muss-e… #AI #Podcast

👉 "Can You Tell the Difference? Contrastive Explanations for ABox Entailments" by Patrick Koopmann, Yasir Mahmood, @NgongaAxel & Balram Tiwari Wishing you a great time and many inspiring exchanges with the AI community! 🚀 #DICEontour #AI #Research #AAAI2026 (2/2)

We’re excited that our colleague @Yaa_Siir is presenting two papers at the AAAI Conference in Singapore! 🇸🇬 👉 "Structure-Aware Encodings of Argumentation Properties for Clique-width" by Yasir Mahmood, Markus Hecher, Johanna Groven & Johannes K. Fichte (1/2)

✨𝗛𝗮𝗽𝗽𝘆 𝗛𝗼𝗹𝗶𝗱𝗮𝘆𝘀 𝗳𝗿𝗼𝗺 𝗗𝗜𝗖𝗘✨ As 2025 comes to an end, we’d like to thank everyone who contributed to a great year of research, collaboration, and exchange. We wish you happy holidays and a wonderful start to 2026! 🎄🚀

✨𝗗𝗜𝗖𝗘 𝗶𝗻 𝟮𝟬𝟮𝟱 – 𝗬𝗲𝗮𝗿 𝗶𝗻 𝗥𝗲𝘃𝗶𝗲𝘄 (𝗣𝗮𝗿𝘁 𝟮) 🚀 New project Learn2RAG launched 🎉 Public engagement at 100 years Heinz Nixdorf 🌍 Research presented at IJCAI, ECML PKDD, ISWC, K-CAP 📈 100K+ downloads for DICE Embeddings, Ontolearn & OWLAPY On to 2026!🚀

✨𝗗𝗜𝗖𝗘 𝗶𝗻 𝗥𝗲𝘃𝗶𝗲𝘄 𝟮𝟬𝟮𝟱 (𝗣𝗮𝗿𝘁 𝟭) 🌍 Research presented worldwide (eg COLING & ESWC) 🤝 Prof. Tibebe Beshah Tesema as SAIL Fellow 👥 Growing team & new members 🚀 EU project ENEXA successfully completed 🎓 PhD defence by @kouagou_dah Stay tuned for Part 2!

5. "NL2LS: LLM-based Automatic Linking of Knowledge Graphs" by Reda Ihtassine, @affia007, Nikit Srivastava, @engr_manzoor, @NgongaAxel & @MAhmedSherif. 🔗dl.acm.org/doi/10.1145/37… With this, we wrap up K-CAP 2025 and our final conference of the year.🙌 (5/5)

4. “Explainable Benchmarking through the Lens of Concept Learning” by Quannian Zhang, Michael Röder, Nikit Srivastava, N'Dah Jean Kouagou & @NgongaAxel. 🔗dl.acm.org/doi/10.1145/37… (4/5)

We’re proud to have been part of K-CAP 2025 in Dayton, Ohio, presenting five papers from DICE! 🚀 1) “Parameter Averaging in Link Prediction” by Rupesh Sapkota, @_CaglarDemir, Arnab Sharma & @NgongaAxel. 🔗dl.acm.org/doi/10.1145/37… (1/5) #DICEontour #DICEreadme #KCAP2025

"OWLAPY: A Pythonic Framework for OWL Ontology Engineering" by Alkid Baci, Luke Friedrichs, @_CaglarDemir & @NgongaAxel is now online! 👉Check it out: arxiv.org/abs/2511.08232 🔎 OWLAPY is a comprehensive Python framework for OWL ontology engineering, already over 50k downloads!