🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Three papers from my group in ICTIR and SIGIR .. 1/ with Yumeng Wang Lijun Lyu , investigates the brittleness of neural rankers.. fun fact: recurring adversarial words like “acceptable” demotes relevant documents .. #ictir2022 L3S Research Center @L3S_Research_Center@wisskomm TU Delft

2/ wanna train Neural re-rankers but only have small training data ? with abhijitanand Jurek Leonhardt Koustav Rudra we propose supervised contrastive losses for data augmentation methods to training cross encoders. Paper: arxiv.org/abs/2207.03153

2/ we find that simple data augmentation schemes improve performance on a wide variety of small datasets. Interestingly our data augmentation actually only works with ranking supervised contrastive losses (SCL)

I am organising a summer school for Explainable AI. We have a session on explainable IR as well 😀. Register if you want a fun summer school with amazing talks and socials. Link: xaiss.eu If you’re interested I am attending #sigir2022

And we are underway..#xaiss starts with the Keynote from Mihaela van der Schaar on New frontiers in ML interpretability.

Here is the video from my #sigir2022 talk "your #phd and you" youtube.com/watch?v=M2qHyH…

A proud advisor moment for me 😇 ... You fully well deserved it Yumeng Wang .. Cheers to our future adventures.

Today Avishek Anand shares a bit of the history of #InformationRetrieval with TU Delft Web Science & Engineer students -- and I get to visit his class and take a stroll down IR memory lane 😉#aGoodDayAtTheOffice

Explainable Information Retrieval: A Survey 🔗: arxiv.org/abs/2211.02405

Happy to share our survey about explainable IR, comments are appreciated. Avishek Anand Max Idahl Jonas Wallat Yumeng Wang Joshua Ghost

Excited to be at #ECIR2023 to present our paper "Probing BERT for Ranking Abilities" with Fabian Beringer, abhijitanand and Avishek Anand! Paper: link.springer.com/chapter/10.100…

When probing BERT rankers for ranking abilities - such as the ability to estimate BM25 scores - we find these abilities to be best captured at intermediate layers

In a second step, we show that the information where the ability is best encoded can be used to train better ranking models. To do so, we devise a MTL setup where we have the ranking objective on the last layer and switch the layers for the ability (e.g., BM25)

If you want work on XAI for LLMs and fact-checking IAI group Universitetet i Stavanger consider applying for this position or please forward it to someone who may be interested. jobbnorge.no/en/available-j…

Context Aware Query Rewriting for Text Rankers using LLM Proposes context-aware query rewriting with LLMs during training to improve ranking, avoiding expensive LLM inference during query processing. 📝arxiv.org/abs/2308.16753

Reminder! #DIR2023 is almost upon us 😉 Interested in presenting your published work, emerging research direction, & even resources of interest to #IR community during special sessions? Submit the contribution form by October 14. More details: dir2023.github.io/DIR2023/

Amazing value for money ;-). Join us in Delft on NOVEMBER 27 for #dir2023 register soon #tudelft_ai . And thanks #sigir #siks for the generous support