Raphaël Troncy

100+ citations! 🎊 Our survey on Semantic Table Interpretation-a @orange.com & EURECOM collaboration-reviews how to extract meaningful information from tabular data.
Proud to co-author with @rtroncy.bsky.social, Jixiong Liu, Viet-Phi Huynh
🔗 shorturl.at/9Bhnf
#SemanticWeb #KnowledgeGraph #STI

Le message publié par X (ex-Twitter) face à l’enquête française est une manœuvre de désinformation classique doublée d'un aveu (X ne respecte pas la loi) et d'un avertissement (votre droit n'est pas son problème) :
Le message de X ➡️ x.com/GlobalAffairs/...
Décryptage.🧵👇
1/46

Can We Trust the Judges? This is the question we asked in validating factuality evaluation methods via answer perturbation. Check out the results at the #EvalLLM2025 workshop at #TALN2025
Blog: giovannigatti.github.io/trutheval/
Watch: www.youtube.com/watch?v=f0XJ...
Play: github.com/GiovanniGatt...

Thanks to the jury members for having evaluated this work: Elena Demidov, Enrico Motta, Serena Villata, @papotti.bsky.social / co supervised with Pasquale Lisena

The final contribution is a rule-based system that again makes use of fine-grained causal relationships between events for explaining fact-checking results. Evaluated on the #FEVEROUS and #AVeriTeC datasets.

A third contribution is a method that relies on the JoinGT system but incorporates fine-grained causal relationships between events from FARO for generating narratives and stories of events. We demonstrated that qualitatively, the generated summaries are more complete.

This dataset can then be used to fine-tune language models (RoBERTa and REBEL) to be more effective at detecting fine-grained causal relationships between events in texts.
A demonstrator making use of these models is available at demo.kflow.eurecom.fr

A second major contribution is the largest dataset containing fine-grained annotations of causal relationships between events (enable, prevent, intend, directly cause). This dataset comes from common sense (ATOMIC), news corpus (CNC) and synthetic #LLM generated data.

Youssra also investigated how capable #LLMs are for reverse-engineering competency questions and deriving user stories out of formal ontologies. Results demonstrate that recent large models such as GPT4 are effective for general domain.

A first contribution is the Facts and Events Relationships Ontology (FARO) that harmonizes different models representing event relations. This is available at anr-kflow.github.io/faro/

This is #PhD defense day at EURECOM. Youssra Rebboud is defending her 3.5 years research work on causal event relationship modeling, extraction and applications derived from them, scholar.google.com/citations?us...

Odeuropa @ World Expo2025 in Osaka - Odeuropa Odeuropa goes Asia! In the last week of April, 2025, three members of the Odeuropa team (Raphael Troncy, Cecilia Bembibre, and Inger Leemans), travelled to Japan to present the project on the World Ex...

Odeuropa @ World Expo2025 in Osaka, odeuropa.eu/2025/05/odeu... ... blogpost summarizing our journey with @odeuropa.bsky.social by @ingerleemans.bsky.social
#EXPO2025 #scent

L’IA face au climat : solution ou partie du problème ?
imtech.imt.fr/2025/04/29/i...
Cet article revient sur notre participation victorieuse au AI Frugal Challenge en marge du AI Summit sponsorisé par @hf.co @quotaclimat.org et au nouveau projet #ClimateSense

📢A unique fully funded three-years PhD position is open at POLITO and EURECOM.
Title: Enhancing Educational Storytelling with Human-Centered AI in the LLM Era
Application deadline: April 28, 2025
Details: www.linkedin.com/feed/update/...

🗣️📣 Appel à candidatures #SemWebPro !

La conférence semweb.pro est LA journée annuelle de présentations et de rencontres dédiées au #webSémantique dans le monde professionnel 🤓

Le comité de programme souhaite intégrer de nouveaux membres, vous nous rejoignez ?

📧 avant le 30/04 à contact@semweb.pro

Thrilled to announce that our research group will be running the TRIPLET challenge at #ISWC2025! 🗾
@rtroncy.bsky.social EURECOM @orange.com @iritoulouse.bsky.social IBM
#SemanticWeb #KnowledgeGraphs #InformationExtraction #AIChallenge

Last demo to conclude #WAICF2025. Try out CimpleKG to fight #misinformation:
✅ Daily updated data from 77 fact-checking organizations
✅ Links 217k+ misinformation-related documents in 26 lang from 36 countries
✅ 15M+ triples, 263k+ entities & 1M+ textual features

The tool provides an intuitive way of visualizing this data:
✅ Explore electricity consumption across France with an interactive map.
✅ Analyze trends over time with detailed graphs and insights.
✅ Discover similarities between territories.
Check out conso-explorer.tools.eurecom.fr

We have presented @WAICANNES Conso Explorer, a joint work with @edfofficiel.bsky.social #SEQUOIA R&D team, that developed the largest #Knowledge #Graph about #electricity consumption in France.
Billions of #RDF triples coming from #enedis #rte #meteofrance #insee #ign

Opening of the #WAICF2025 by the French Minister on Digital and AI @clarachappaz.bsky.social !
Come visit the booth E24 where EURECOM has an outstanding line up of demos over the next 2 days!

Frugal AI Challenge The goal of the Frugal AI Challenge is to encourage both academic and industry actors to keep efficiency in mind when deploying AI models. By tracking both energy consumption and performance for diffe...

More about the challenge: frugal-ai-challenge.github.io
What’s more? We open source our winning solution and alternative attempts! Check out github.com/D2KLab/fruga...

What a day at the #AI #Summit! Thrilled to report that EURECOM won the AI Frugal Challenge organized by @hf.co
Our task: detect misinformation about climate change in texts
The catch: be accurate but be very energy savvy!
More to come with #ClimateSense, a new EU project

At the #AISummit Business Day listening the French and German minister of economic affairs. Proud to represent EURECOM for demonstrating #EULER, our innovative LLM-RAG tuned for Socratic interactions that aims to improve how students learn our graduate courses! #ai #education

The Holonet Galactic Encyclopedia has been named "Tool of the Week" by #Wikidata! 🎉
m.wikidata.org/wiki/Wikidat...
Huge thanks for the spotlight! 🙌 Stay tuned, fellow #StarWars fans and #KnowledgeGraph enthusiasts, more features are coming soon! 🌌
Try it: holonetgalacticmap-frontend.vercel.app

list of tropes with examples from social posts

Tropes, such as "Hidden Motives", are recurring narrative elements used to evoke familiar patterns in communication

Our #COLING paper uncovers that tropes are used in 37% of the social posts debating immigration and vaccination
📄 coling-2025-proceedings.s3.us-east-1.amazonaws.com/main/pdf/202...
👇

Socrates teaching its method

Meet EULER (EURECOM Language Model for Education and Research) and our new #Socratic LLM for AI-Driven Education, eurecom-blog.medium.com/eurecoms-soc...
Model available @huggingface.bsky.social and @ollama.bsky.social
#LLM #RAG #EduTech

What are data spaces and what do they do? Learn more about data spaces: what they are, what they do and what’s next.

Great blog post from @odihq.bsky.social @esimperl.bsky.social on the current development state of #dataspaces in Europe.

theodi.org/news-and-eve...

Fantastic talk from Serena Villata at the #SophiaSummit who is presenting the state of the art in argument mining. Datasets and tools available such as DispuTOOL and USElecDeb60To20. Supervised #BERT based models are still better than LLMs in particular for argument reasoning

More importantly, Julien is presenting a unique evaluation grid for qualitatively evaluating the #ontology automatically built by LLMs. Main results: ontologies are often too flat and insufficiently specific. #semwebpro
Check out www.lettria.com for a demo

Ontology Toolkit from LettrIA

Can #AI and #LLM be used to facilitate the knowledge engineering process? Julien Plu from #LettrIA is presenting the ontology toolkit that leverages LLM to generate competency questions, classes, properties and their axiomatization using solely documents and a description of the domain.