🔥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

Today in SIGIR 2025 at M3.1, I will briefly introduce our newly published collection FeB4RAG! The collection is the first collection to evaluate Federated search in RAG. Our resource support evaluation of Resource Selection, Merging, and Human Evaluation on Answer Generation!

Now Shengyao Zhuang presenting our setwise LLM ranker at #sigir2024

Today the #SIGIR2024 main program starts. We are presenting several papers -- come to check them out

Wang shuai (Dylan) is now sharing his new resource paper ‘FeB4RAG’ for federated search SIGIR 2025 Check paper: arxiv.org/abs/2402.11891 and dataset github.com/ielab/FeB4RAG

ESSIR 2024 made their videos publicly available!!! They'll add more in the near future 😍 #essir2024 youtube.com/playlist?list=…

Delighted to share our full paper "An Investigation of Prompt Variations for Zero-shot LLM-based Rankers" w/Shengyao Zhuang Wang shuai (Dylan) Guido Zuccon has been accepted at ECIR2025! Huge thanks to co-authors. Check it out if you're into prompt variations & LLM-rankers. #ecir2025

Thank you so much Guido Zuccon ! It was great to collaborate with you and ieLab members Wang shuai (Dylan) Shengyao Zhuang ! Hope to see you soon and work together again. 😁

Really excited that SIGIR-AP will be in Xi’an China this year. Hope to explore the culture and food 😍

Nice work for LLM-based rankers 😃

GPT-4.1 API has been released. Seems like better instruction following ability based on their internal evaluation 😃

Gemini Advanced is now free for college students in the U.S. The best part: This offer isn't just for finals this semester. Sign up before June 30, 2025, and you’ll get free access all the way through spring finals 2026. Terms apply.

Thinking budget is cool. Now experiments with reasoning model may be relatively affordable?

Proceedings of #CHIIR2025 ACM SIGIR ACM CHIIR 2025 are now available at the ACM Digital Library: dl.acm.org/doi/proceeding…

ELLIS ESSIR 2025, the European Summer School on Information Retrieval, is taking place in Wolverhampton, UK, July 7–11. Don't miss exciting lectures and tutorials around IR, AI, UX, etc! More info 👉 2025.essir.eu #InformationRetrieval #AI

Did you know that fine-tuning retrievers & re-rankers on large but unclean training datasets can harm their performance? 😡 In our new preprint, we re-examine popular IR training data quality by pruning datasets and identifying and relabeling 𝐟𝐚𝐥𝐬𝐞-𝐧𝐞𝐠𝐚𝐭𝐢𝐯𝐞𝐬! 🏷️

🚨Wouldn’t it be nice if your agentic search system could reason over all your docs? ✨Introducing Rank-K, a listwise reranker that benefits from test-time compute and long-context! Rank-K sets a new SoTA for reasoning-based reranking, without reasoning chains from other models.

🧵1/5 🚨 Excited to announce our SIGIR 2025 resource paper: "𝙍𝙖𝙣𝙠𝙇𝙇𝙈: 𝘼 𝙋𝙮𝙩𝙝𝙤𝙣 𝙋𝙖𝙘𝙠𝙖𝙜𝙚 𝙛𝙤𝙧 𝙍𝙚𝙧𝙖𝙣𝙠𝙞𝙣𝙜 𝙬𝙞𝙩𝙝 𝙇𝙇𝙈𝙨" is now on arXiv! 🎉 📄 Paper: arxiv.org/abs/2505.19284 💻 Code: github.com/castorini/rank… 📦 PyPI: pypi.org/project/rank-l…

IR is moving so fast! It was only March that we released Rank-R1; in April ReasonIR came up; May is not finished yet and we release v0.2 of Rank-R1, SOTA on BRIGHT leaderboard Shengyao Zhuang Xueguang Ma Bevan Koopman Jimmy Lin Guido Zuccon ielab update to preprint soon

It was really nice to collaborate with Oleg Zendel, Damiano Spina 🦋@damianospina.com, Kun, and Khoi Nguyen. Our work, GRAG, was named one of the finalists of the #LiveRAG Challenge at the #sigir2025 SIGIR 2025. Have a look at the paper and chat with us SIGIR 2025 if you are interested!

NeurIPS D&B track in a nutshell: (1) An LLM-generated benchmark dataset (2) used to test performance of LLMs (3) evaluated via LLM-as-a-judge