Data, Intelligence, and Graph Team @ Télécom Paris

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

06.01.2026 10:44 — 👍 1    🔁 1    💬 0    📌 0

Large Language Models (LLMs) may one day replace search engines as the primary portal to information on the Web. In this opinion paper, we investigate the societal challenges that such a change could bring. We focus on the roles of LLM Providers, Content Creators, and End Users, and identify 15 types of challenges. With each, we show current mitigation strategies – both from the technical perspective and the legal perspective. We also discuss the impact of each challenge and point out future research opportunities.

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 !

07.12.2025 09:18 — 👍 4    🔁 3    💬 0    📌 0

T-REX: Table - Refute or Entail eXplainer

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

19.06.2025 18:50 — 👍 3    🔁 1    💬 0    📌 0

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.

17.12.2025 09:42 — 👍 2    🔁 1    💬 0    📌 0