DIG researchers and collaborators have three new accepted articles: one in ACM Journal on Computing and Cultural Heritage, and two at LREC 2026. Congratulations to all authors! 1/4 #LREC2026 #JOCCH #NLP #KnowledgeGraphs

The team of Knowledge-Aware AI of TU Dresden visited us for a two-day workshop to explore the synergies between language models and knowledge bases. Come visit us again!

We were happy to host Julia Stoyanovich, director of the Center for Responsible AI at New York University, in the DIG seminar for her talk on Uncertainty in the Data Engineering Pipeline: From Imputation to Explanation.

Welcome to Capucine Brillet, new PhD student at DIG! She will work on language models and knowledge bases, inspired by cognitive science. She joins us after studying mathematics at Université Paris Cité and working at ENS.

We were happy to host Robert Wrembel from Poznan University of Technology (PUT) for an inspiring talk on Data Integration: Remaining Challenges and Research Paths.

Congratulations to our researchers on their accepted paper at IJCAI 2026 demo track! Zacchary Sadeddine and Fabian M. Suchanek: “Neuro-Symbolic Logical Reasoning with Textual Entailment (VANESSA)” Link: suchanek.name/work/publica... #IJCAI2026

Congratulations to our researchers on their accepted paper at IJCAI 2026 demo track! Samy Haffoudhi, Nikola Dobričić, Fabian Suchanek, and Nils Holzenberger: “LELA: An End-to-end LLM-based Entity Linking Framework with Zero-shot Domain Adaptation” Link: suchanek.name/work/publica... #IJCAI2026

We are excited to announce that the DIG team will co-organize the HiParis Symposium on Generative AI for Biochemistry and Health! For more details, refer to the official event link: hi-paris.fr/research/sym...

We are excited to announce that the DIG team will co-organize the 10th workshop on Automated Knowledge Base Construction (AKBC 2026)! It will take place at EMNLP 2026 in Budapest, and accepts vision, regular, and challenge papers. For more details, refer to the Workshop Link: www.akbc.ws/2026/.

We were happy to host Elena Simperl from King’s College London for an inspiring talk on Designing Better Knowledge Engineering Assistants.

Congratulations to Mehwish Alam for her successful Habilitation defense entitled "The Knowledge in Neurosymbolic Artificial Intelligence"!

Mohamed Islem KARA BERNOU is joining the DIG team for a PhD to work on verifying the outputs of language models with the help of knowledge bases. Welcome, Mohamed Islem KARA BERNOU!

We're happy to welcome Chenwei Wan to the DIG team as a research engineer! Chenwei will work on Non-named entity representation in knowledge bases, with the goal to start a thèse CIFRE with Schlumberger. Welcome, ChenWei!

Congratulations to Marc Jeanmougin and Théo Zimmermann for receiving the “Engagement, Pedagogy, and Teaching” award (emerging initiative category) from Institut Mines-Télécom (IMT) for their innovative course on open-source contributions!

Congratulations to Cristian Santini, Marieke van Erp, and Mehwish Alam for their EACL 2026 paper “It's All About the Confidence: An Unsupervised Approach for Multilingual Historical Entity Linking using Large Language Models”! PDF preprint at arxiv.org/pdf/2601.08500 #LLM

We're happy to launch our revamped BlueSky channel, Mastodon channel, and Website! Follow us for news on knowledge graphs, language models, foundational models, learning over tabular data, graph representation learning, graph mining, and stream mining! Web site and links: dig.telecom-paris.fr

DATA, INTELLIGENCE & GRAPHS

Research Team @ Institut Polytechnique de Paris

dig.telecom-paris.fr

Our article "It's All About the Confidence: An Unsupervised Approach for Multilingual Historical Entity Linking using LLMs" has been accepted to #eacl2026 Cristian Santini & Marieke van Erp. MHEL-LLaMo uses a combination of #slms and #llms for entity linking. Preprint: tinyurl.com/2h8uphyh

Our article on the societal challenges posed by Large Language Models is now available at SIGIR Forum: sigir.org/wp-content/u... Thanks to Zacchary Sadeddine, Winston Maxwell and @gaelvaroquaux.bsky.social !

Thrilled to announce that our paper on “T-REX: Table – Refute or Entail eXplainer” w/ Tim Luka Horstmann and Baptiste Geisenberger has been accepted at #ecmlpkdd2025 - Demo track. It performs verification of factual claims over tabular data using #opensource #llms GitHub: shorturl.at/t715r

Hello World! Welcome to the Bluesky page of Data, Intelligence, and Graph team at Tèlècom Paris, Institut Polytechnique de Paris. Stay tuned for the highlights of the scientific activities of our team. For more details visit our website linked in Bio.