Mathias Vast retweeted
Understanding Matching Mechanisms in Cross-Encoders
@MathiasVast1 et al. investigate how neural ranking models construct relevance signals by analyzing attention processes and extracting causal insights in cross-encoders.
📝 arxiv.org/abs/2507.14604
👨🏽💻git.isir.upmc.fr/mat_vast/si…
Mathias Vast retweeted
"Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders"
by @MathiasVast1, @basilevancooten , @LaureSoulier, @bpiwowar in collaboration with @sinequa
Published at @acm_ictir with oral presentation!
➡️arxiv.org/abs/2406.19309
Mathias Vast retweeted
Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders
Adapts Integrated Gradient methods to interpret MonoBERT for IR, identifying specific neurons responsible for relevance assessment and OOD handling.
📝arxiv.org/abs/2406.19309
Just came back from Washington and the @SIGIRConf + @acm_ictir conferences where I have had the chance to present our last paper "Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-Encoders" during the ICTIR day. (1/4)
1
1
70
Amongst other things, we observed that relevant passages and non-relevant passages are treated by different neurons, OOD predictions involve additional neurons compared to ID and the important neurons are localized mostly in 2 regions of the model (middle and last layers). (3/4)
1
34
More details in the paper: arxiv.org/abs/2406.19309
Code and slides of the ICTIR's presentation are also available here: git.isir.upmc.fr/mat_vast/ri…
(4/4)
32
Mathias Vast retweeted
The list of #ICTIR2024 accepted papers is now available online:
ictir2024.org/program/accept…
Looks like we have an excellent program coming up!😎🤓
Mathias Vast retweeted
The last Sentence Transformers release introduced GISTEmbedLoss by @avsolatorio, which allows for training models that outperform those trained by the wildly popular in-batch negatives loss (MultipleNegativesRankingLoss). Learn about it in this 🧵(links at the bottom):
Mathias Vast retweeted
Suite des présentations avec @MathiasVast1 sur l’adaptation de domaine avec un modèle de RI parcimonieux
coria.asso-aria.org/2024/art…
Mathias Vast retweeted
All done! It's a wrap from #ecir2024. We've had a brilliant 5 days with loads of great talks, discussions, and social events.
Thanks to everyone that made #ecir2024 such a great success! We hope you all enjoyed Glasgow. Looking forward to seeing you again in Lucca for #ecir2025 – at Glasgow, Scotland
Mathias Vast retweeted
If you still have the energy after all the nice presentations from today's sessions and keynote, don't hesitate to come and discuss with @MathiasVast1 during the poster session later today @ecir2024 !
Mathias Vast retweeted
(3) Simple Domain Adaptation for Sparse Retrievers by @MathiasVast1, @zongyuxuan3, @basilevancooten @bpiwowar and @LaureSoulier
arxiv.org/abs/2401.11509
w/ @sinequa
Mathias Vast retweeted
"Simple Domain Adaptation for Sparse Retrievers" - our new research published as a preprint @arxiv
arxiv.org/abs/2401.11509
#informationretrieval #enterprisesearch #NLP #RAG #MachineLearning #BERT #Knowledgemanagement
Mathias Vast retweeted
The year 2023 is drawing to a close.
Before we head off on vacation, let's take a look back at the year:
(1/5) Our ML/DL team has grown with the arrival of:
- François Yvon @yvofr, CNRS research director
- Caio Corro @UndefBehavior & Alasdair Newson, lecturers @SorbonneParis1
Mathias Vast retweeted
The list of accepted papers is now available at: ecir2024.org/accepted-paper/
Lots of really interesting work to be presented at #ecir2024
I am thrilled to share that my first paper "Simple Model Adaptation for Sparse Retrievers" in collaboration with @zongyuxuan3 @bpiwowar and @LaureSoulier has been accepted in the "short papers track"! Special thanks to @basilevancooten too for the supervision #ecir2024
Mathias Vast retweeted
#essir2023 group work and hands-on day: senior PhD students from @ProjectDossier lead work on domain-specific use cases @essir_eu – at Vienna, Austria


























