Research scientist at @naverlabseurope. Interested in NLProc, Machine Learning, Information Retrieval. Any pronouns.
Grenoble, France
Joined November 2014
- Tweets538
- Following818
- Followers414
- Likes2.8K
Thibaut Thonet retweeted
🚀 Research intern opening @NAVERLABSEurope (Grenoble, 5–6 months)
Topic: enforcing hard constraints in LLMs while preserving quality
Looking for:
🎓 PhD (or exceptional MSc) student
🧠 LLMs + PyTorch
📚 RLHF / alignment methods
📍 Onsite only
apply → lnkd.in/dPf3DfDd
🎉 Delighted to share that our work “FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data” has been accepted to #EMNLP2025 main!
🧑🏻💻 Joint work with @germank, @josrzn, Pierre Erbacher, @MarcDymetman
📄 Preprint: arxiv.org/abs/2508.04698
Thibaut Thonet retweeted
🚀 AutoMin 2025 – 3rd Edition of the Automatic Minuting Shared Task at #SIGDIAL2025!
@naverlabseurope & UTTER push LLMs in:
📌 Meeting Summarization
📌 Meeting QA
📅 Aug 28, 2025
Join the future of NLP, AI & Meeting Understanding! 🔗 ufal.github.io/automin-2025/
#NLP #LLM #UTTER
Thibaut Thonet retweeted
Still possible to join this shared task !
Join AutoMin 2025 - 3d Run of the Automatic Minuting Shared Task at #SIGDIAL2025 to push the limits of LLMs in
📌 Meeting Summarization
📌 Meeting Question Answering
📅 Workshop: Aug. 28, 2025
ufal.github.io/automin-2025/
#NLP #LLMs #AI #AutoMin
Thibaut Thonet retweeted
Join AutoMin 2025 - 3d Run of the Automatic Minuting Shared Task at #SIGDIAL2025 to push the limits of LLMs in
📌 Meeting Summarization
📌 Meeting Question Answering
📅 Workshop: Aug. 28, 2025
ufal.github.io/automin-2025/
#NLP #LLMs #AI #AutoMin
Thibaut Thonet retweeted
Excited to share that Provence is accepted to #ICLR2025!
Provence is a method for training an efficient & high-performing context pruner for #RAG, either standalone or combined with a reranker
huggingface.co/blog/nadiinch…
w/ @thibault_formal @VNikoulina @sclincha @naverlabseurope
Absolutely delighted to share that our work on Guaranteed Generation from LLMs has been accepted at #ICLR2025 😍
openreview.net/forum?id=8roR…
TL;DR: a new method for ensuring strict constraint satisfaction in LLMs while preserving their original generative capabilities
If you're looking for an internship and interested in working on related topics (controlled text generation, constraint processing in LLMs), make sure to check our internship offer: teapawt.org/tthonet/status/1882097…
🚨 Excited about ML/NLP and looking for a research internship on controlled text generation?
Come work with us on advanced constraint processing in large language models at NAVER LABS Europe!
✨ Learn more and apply here: europe.naverlabs.com/job/2-7…
🚨 Excited about ML/NLP and looking for a research internship on controlled text generation?
Come work with us on advanced constraint processing in large language models at NAVER LABS Europe!
✨ Learn more and apply here: europe.naverlabs.com/job/2-7…
Thibaut Thonet retweeted
We are #hiring for Internship: Advanced Constraint Processing in LLMs at Naver Labs Europe. We are attending @coling2025 if you would like to meet! - via #Whova event app
Thibaut Thonet retweeted
I'll present two papers at the main @coling2025 conference next week: (1) ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models (w/ @tthonet and @josrzn) - see arxiv.org/abs/2403.20262 and github.com/utter-project/ELI…
Thibaut Thonet retweeted
If you are at #EMNLP2024 and interested in RAG, come to discuss our BERGEN library!
@VNikoulina will present the BERGEN poster tomorrow, Nov 13, 16:00-17:30, location: Jasmine
Repo: github.com/naver/bergen
Paper: aclanthology.org/2024.findin…
@naverlabseurope #NLProc #RAG
Thibaut Thonet retweeted
We have an open research internship position at Naver Labs Europe, in Grenoble, France!
Apply to work on improving #RAG for multilingual and/or multi-domain settings!
europe.naverlabs.com/job/3/
Vassilina could tell about it at her poster tomorrow #EMNLP2024, Nov 13, 16:00-17:30
If you are at #EMNLP2024 and interested in RAG, come to discuss our BERGEN library!
@VNikoulina will present the BERGEN poster tomorrow, Nov 13, 16:00-17:30, location: Jasmine
Repo: github.com/naver/bergen
Paper: aclanthology.org/2024.findin…
@naverlabseurope #NLProc #RAG
Thibaut Thonet retweeted
📢 Job Alert 📢 @naverlabseurope
My team is looking for a Research Scientist in Visual Representation Learning - More info tinyurl.com/3jz935fk
Thibaut Thonet retweeted
🧵 Excited to share PRISM, our new methodology for auditing biases in Large Language Models, as part of @PHAWM_project w/@leifos. This flexible, role-based framework can be tailored to audit biases on political, social, or any dimensions. @responsibleaiuk arxiv.org/abs/2410.18906
Thibaut Thonet retweeted
What’s a good baseline for RAG? 🤔
The literature shows consistent differences in experimental setups, retrievers, datasets, and metrics. So, we built the BERGEN library github.com/naver/bergen to enhance reproducibility and identify strong baselines : 🧵
@naverlabseurope
Thibaut Thonet retweeted
We offer this 1y postdoc to work with us on the @UTTERProject EU project on LLM-based agents ! Come work with us on 1 or several of these topics: i] managing uncertainty and ambiguity ii] improving the use of conversational context iii] ensuring the safety and alignment of LLMs.
📢 Open position! PostDoc position in #LLM powered conversational agents @naverlabseurope Grenoble, France. @UTTERProject ***Please share***
Start date: September
Duration: 1yr
More info & how to apply: europe.naverlabs.com/job/pos…
Thibaut Thonet retweeted
📢 Open position! PostDoc position in #LLM powered conversational agents @naverlabseurope Grenoble, France. @UTTERProject ***Please share***
Start date: September
Duration: 1yr
More info & how to apply: europe.naverlabs.com/job/pos…
Thibaut Thonet retweeted
😀We're looking for a talented researcher to join our team at Naver Labs Europe (@naverlabseurope) , working on LLMs and Retrieval!😃
Please apply here: europe.naverlabs.com/job/res… !
Thibaut Thonet retweeted
After spending just 20 minutes with the @MistralAI model, I am shocked by how unsafe it is. It is very rare these days to see a new model so readily reply to even the most malicious instructions. I am super excited about open-source LLMs, but this can't be it!
Examples below 🧵
Mistral 7B is out. It outperforms Llama 2 13B on every benchmark we tried. It is also superior to LLaMA 1 34B in code, math, and reasoning, and is released under the Apache 2.0 licence.
mistral.ai/news/announcing-m…
