Prof and Researcher at @EURECOM. AI, Knowledge Graph, Open Data, LLM, Information Extraction, Recommender Systems, https://xitter.cf/t.co/CgUPPwuBlP
Sophia Antipolis (FR)
Joined May 2009
- Tweets7.5K
- Following464
- Followers2.6K
- Likes1.2K
From #Disinfo2026, some government sponsors of the conference are hidden with white stickers under the pressure of the US Government, which does not like we talk about misinformation and FIMI when it is from US state.
Full coverage of this story, theguardian.com/us-news/2026…
Raphaël Troncy retweeted
letudiant.fr/etudes/fac/the-…
@EURECOM entre dans le classement du THE directement au 231e rang mondial ex aequo. Et au 5eme rang français ! C’est la meilleure entrée européenne de l’édition 2027 parmi les nouveaux établissements classés.
Raphaël Troncy retweeted
(1/n)
The number of research papers has gone wild. All generated by AI?
I pulled stats from CVPR/ICCV/ECCV, NeurIPS/ICML/ICLR, SIGGRAPH/SA/ToG since 2006: 119k papers + 460k arXiv preprints
Accepted/yr: 968 (2006) → 19,003 (2025) → 18,976 (2026 so far)
Quite surprising ->🧵
Raphaël Troncy retweeted
🚀 #TheWebConf2026 is officially underway!
We're kicking off the conference with an exciting morning of Tutorials and Workshops across multiple virtual halls.
📅 Check the full schedule and join your sessions
Have a great first day—we'll see you online!
#TheWebConf2026
🤖 Made with AI
🚨 Can we trust LLM-generated ontologies?
At #ESWC2026 / #llms4kgoe, I presented:
"Pitfalls in AI-Generated Ontologies: Strategies for Detection and Mitigation" where I discuss how to detect and mitigate common mistakes in AI-generated ontologies
Slides: bit.ly/lettragraph-llms4kgoe
Key Results:
🔎 Ontology Pitfalls Detector
github.com/D2KLab/Ontology-P…
🛠️ Ontology Toolkit by Lettria
perseus.lettria.com/
Joint work with @PasqLisena, @julienplu
#KnowledgeGraphs #OntologyEngineering #LLMs #ESWC2026 #llms4kgoe
Slides from my #LLMText2KG 2026 keynote at @eswc_conf are online: “From Strings to Knowledge Graphs: What Text2KG Still Gets Wrong.”
drive.google.com/file/d/16kM…
Try #PERSEUS for Text2KG experiments:
GitHub: github.com/Lettria/perseus-c…
Docs: docs.perseus.lettria.net/
#KnowledgeGraphs #LLMs
📣 Join us at TRIPLET 2026 @eswc_conf in Dubrovnik!
🌟 Keynote by @pgroth !
🏆 TRIPLET Challenge presentations
🥇 Leaderboard winners announced for Task 1 and Task 2
📅 11 May 2026
🔗 ecladatta.github.io/triplet2…
#TRIPLET2026 #ESWC2026 #SemanticWeb #KnowledgeGraphs #NLP #MultimodalAI
Glad to be in the #PhD committee of Eric Behar who worked on Job—Applicant recommender systems,
samovar.telecom-sudparis.eu/…
Raphaël Troncy retweeted
Une étude (French et al., Information Systems Frontiers 2025) propose un modèle puissant pour comprendre comment nous consommons les fake news sur les réseaux sociaux.
Spoiler: ce n’est pas une question de crédulité. C’est une question d’émotions.
link.springer.com/article/10…
EURECOM and EDF built France’s largest energy #knowledgegraph powering a new era of energy intelligence, read on at
eurecom-blog.medium.com/eure…
Great collaboration between @EURECOM and the SEQUOIA R&D team at @EDFofficiel #research #energy
Hosted by the wonderful @merpeltje & @IngerLeemans at @huygens_knaw to celebrate @odeuropa prize at the @europanostra 2025 in the Research category. Thanks to Elena Binachi and Maximilian Voigt from @EU_Commission to celebrate with us 🏆
… and the plaque found its way into the vitrine of the beautiful library before touring in Europe and soon to be seen at @EURECOM !
Raphaël Troncy retweeted
100+ citations! 🎊 Our survey on Semantic Table Interpretation-a @Orange_Future & @EURECOM collaboration-reviews how to extract meaningful information from tabular data.
Proud to co-author with @yansera1 @rtroncy @vp_huynh.
🔗shorturl.at/9Bhnf
#SemanticWeb #KnowledgeGraph
Excited to have presented the Text2KGBench-LettrIA benchmark at the KB-LLM workshop at @iswc_conf. ~5k sentences annotated with respect to 19 ontologies to train #LLMs to build Knowledge Graphs.
#iswc2025
Paper: ceur-ws.org/Vol-4041/paper3.…
Slides: bit.ly/Text2KGBench-LettrIA
We have then compared numerous closed LLMs (@claudeai @GeminiApp @ChatGPTapp) with fine-tuned open weights LLMs (@MistralAI @Alibaba_Qwen Gemma3, Phi4). There are clearly 2 leagues: fine-tuned specialized models OUTPERFORM larger closed models and are more efficient.
#iswc2025
We released our best fine-tuned model, named PERSEUS. Benchmark results detailed at lettria.com/benchmarks/bench…
Joint work between @EURECOM and @lettria_fr as part of the #LettRAGraph project funded by @Bpifrance #iswc2025
Very proud to have presented with @IngerLeemans @odeuropa
selected among the 4 winners in the Research Category! We developed digital tools to recognize smell experiences in images and texts and we reconstructed scents from the past! @EURECOM
👋 Hi from Brussels! 🇧🇪 We’re thrilled to be hosting the #EuropeanCulturalHeritageSummit2025, starting with the Excellence Day showcase of our 30 #EuropeanHeritageAwards laureates.
Our high-level Awards Ceremony is tomorrow!
🎥 Bookmark the livestream: europanostra.org/events/euro…
Raphaël Troncy retweeted
If you are at @ACMRecSys, pass by spot #21 and try our demo for generating your playlist by choosing its title in Natural Language.
demo online playlist-recommendation.tool…
@rtroncy
@RebboudY #musicReccomendation #ai #recsys – at Prague, Czech Republic
Raphaël Troncy retweeted
Exploiting playlist titles can push good recommendation and feed a cold-start strategy for #playlist generation.
Check our presentation of this morning at @ACMRecSys + code and links at last slide
bit.ly/lmrec-2025
// cc @rtroncy #recsys #ai
