Delighted to deliver the keynote at the QPP++ workshop ECIR2025. Shared my view on the role of QPP models for Adaptive IR and RAG systems - building on our last year's SIGIR perspective tinyurl.com/yc8ne3bz w/ Andrew Parry & Manish Chandra. Slides: tinyurl.com/4t23dj2y

Happy to share some of the ongoing work of Fangzheng Tian w/ Craig Macdonald as a vision for the potential of applying #qpp for adaptive #rag. For those who missed the talk, here're the slides: gdebasis.github.io/files/ragtalk.… #ecir2025 Glasgow IR Group

Finishing up #ECIR2025 for Glasgow IR Group is Andreas Chari talking about his work (w/ Sean MacAvaney & Iadh Ounis) on improving low-resource retrieval with linguistic similarity transfer! A great end to the conference! Glasgow IR Group @glasgowcs

Today, Debasis Ganguly Debasis Ganguly from the University of Glasgow is giving an #IRTalk entitled "The Role of Query Performance Prediction in Developing Adaptive Search and RAG Systems". Details: samoa.dcs.gla.ac.uk/events/viewtal… UofG Computing Science Glasgow IR Group

🚨 New Pre-Print! We show that in-context learning can steer LLM rankers to satisfy multiple objectives at once, relevance and fairness/diversity, without any parameter updates. Work done jointly with Nilanjan Sinhababu from IIT Kharagpur and Debasis Ganguly. 🧵 Below!

🚨 New Pre-Print! You've just added your 600th model to your negative mining pool and filtered all false negatives. Does any of this even matter when we can apply distillation? In this work with Debasis Ganguly and Sean MacAvaney, we explore data selection in modern ranking. 🧵 Below

❓Which retrieval library should you use for RAG? Which agent library? Where do you get datasets? We made PyTerrier RAG to stop your headaches! Led by Craig Macdonald /w (Jinyuan Fang , me and Zaiqiao Meng )! 🧵 ⬇️

At 15:00 on 7th July, Florin Cuconasu from Sapienza University of Rome will give an #IRTalk entitled "Beyond Relevance: Understanding the Distracting Effect of Retrieved Passages in RAG Systems". Details: samoa.dcs.gla.ac.uk/events/viewtal… UofG Computing Science Glasgow IR Group

Today, Florin Cuconasu Florin Cuconasu from the Sapienza University of Rome Sapienza Università di Roma is giving an #IRTalk entitled "Beyond Relevance: Understanding the Distracting Effect of Retrieved Passages in RAG Systems". Details: samoa.dcs.gla.ac.uk/events/viewtal… UofG Computing Science Glasgow IR Group

Am I on the Right Track? What Can Predicted Query Performance Tell Us about the Search Behaviour of Agentic RAG Fangzheng Tian et al. examine how query performance prediction can provide insights into the search behavior of agentic RAG systems. 📝arxiv.org/abs/2507.10411

How does retrieval impact on Agentic RAG? Let's see what predicted intermediate retrieval quality can tell us! Our IR-RAG@SIGIR'25 paper is on Arxiv: arxiv.org/abs/2507.10411. #SIGIR2025 cc/ Jinyuan Fang Debasis Ganguly Zaiqiao Meng Craig Macdonald

.Fangzheng Tian is presenting our work on using QPP in agentic RAG w/ Jinyuan Fang Debasis Ganguly Zaiqiao Meng 📄 arxiv.org/abs/2507.10411

Now time for Glasgow IR Group 's Fangzheng Tian to present his impeccable QPP work "Am I on the Right Track?" at the IR-RAG Workshop #SIGIR2025 (work w/t Jinyuan Fang, Debasis Ganguly, Zaiqiao Meng and Craig Macdonald)

After attending the panel at the Explainability for IR workshop, now attending my student's talk at the IR4RAG workshop. This paper is a first step towards building an adaptive multi-agent RAG pipeline. Craig Macdonald Fangzheng Tian

The welcome reception at #ICDCS2025 is buzzing with energy! Fantastic to see so many smiling faces and lively conversations — a vibrant start to the conference. Here's to a great main conference ahead! 🎉

Want your LLMs to be safe and responsibly aligned? Time to vaccinate them! 🧬 Fascinating #ICDCS2025 keynote by Ling Liu (Georgia Tech) on reducing fine-tuning costs while boosting safety in LLM deployment.

Delighted to see my former PhD student at Glasgow IR Group and UofG Computing Science Jingmin Huang, now a lecturer at the University of Southampton; Jingmin served as Demo Co-Chair at #ICDCS2025. Great to catch up at the conference!

Journal article “Unifying Isolated Processes for Enhanced Multi-modal Recommendations Using a Graph Transformer” has been accepted at ACM Transactions on Recommender Systems (ToRS); Joint work with Zixuan Yi  & part of a special issue on best papers from ACM #RecSys 2024

📢 Call For Papers: 1st workshop on Proactive Conversational Information Seeking with Large Language Models ACM CIKM 2025 For more info visit: proactllm.github.io 📅 When: November 14, 2025 📝 Deadline: August 31, 2025 #ProActLLM #cikm2025 #LLM #ProactiveAI #ConversationalAI

Cheers to 15 years of wonderful memories. Join us one last time, Downton Abbey: The Grand Finale is in theaters TODAY. 🎟️: downtonabbey.com