🔥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

Share our paper "ReSLLM: Large Language Models are Strong Resource Selectors for Federated Search" with Shengyao Zhuang , Bevan Koopman and Guido Zuccon has been accepted to TheWebConference 2025 as a short. Preprint: arxiv.org/abs/2401.17645 Github: github.com/ielab/SLAT-RsL…

Beyond this nice realization that the ~continuous~ input space of document embeddings is easier to run adversarial attacks on than on pure text, this paper compares single and multi-vector approaches in terms of robustness which I had never seen in a ML privacy setting before !

Our code is available now: github.com/ielab/dsr-pois…

It's always exciting to learn something new! With Shengyao Zhuang, we explore how recent RL techniquesbecome can help the reranking being more explainable and better handle queries requiring complex reasoning.

I've just ported the excellent monoELECTRA-{base, large} reranker models from Ferdinand Schlatt & the research network Webis Group to Sentence Transformers! These models were introduced in the Rank-DistiLLM paper, and distilled from LLMs like RankZephyr and RankGPT4. Details in 🧵

Our paper has been accepted at #SIGIR2025!

🎉 Excited to share the list of our ielab papers accepted at #SIGIR2025 ACM SIGIR! Topics include efficiency in IR, domain-specific IR (SysRev, podcast), screenshot retrievers, hallucination detection, and more. See you in Padua 🇮🇹! Details coming soon, stay tuned!

Yesterday I presented our #ECIR2025 paper "An Investigation of Prompt Variations for Zero-shot LLM-based Rankers", with Shuoqi Sun Shengyao Zhuang Wang shuai (Dylan). Yes, it was in a church! Slides at ielab.io/files/guido-20… and paper at arxiv.org/abs/2406.14117

Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality Xueguang Ma et al. introduce a unified pipeline enabling researchers to explore retriever models at different scales, languages, modalities 📝arxiv.org/abs/2505.02466 👨🏽‍💻github.com/texttron/tevat…

One embedding model for all modalities and cross different languages! We will demo the model training pipeline in #SIGIR2025 Our OmniEmbed-v0.1 also demonstrate very strong performance on MAGMaR multimodal retrieval shared task eval.ai/web/challenges…

Our paper has been accepted at #ACL2025 main conference!