Looking fwd to my talk on 10th ECIR2025, where I'll be giving a perspective on the potentials of applying #QPP to improve #RAG.

Now Fangzheng Tian is presenting our work on relevance propagated from retriever to generator in RAG w/ Debasis Ganguly Glasgow IR Group #ecir2025

More incredible Glasgow IR Group contributions today at ECIR2025 with Fangzheng Tian now presenting his work with Debasis Ganguly and Craig Macdonald. #ecir2025

Glad to share that "Exploring the Role of Diversity in Example Selection for In-Context Learning" w/ Janak Kapuriya, Manit Kaushik, and Sumit Bhatia has been accepted as a short paper in #SIGIR2025. Arxiv and git link coming soon.

Glad to share that our paper "In-Context Learning as an Effective Estimator of Functional Correctness of LLM-Generated Code" w/ Susmita Das, Madhusudan Ghosh, Priyanka Swami, and Gul Calikli has been accepted as a short paper in #SIGIR2025. Arxiv and code coming soon.

Congratulations to Manish Chandra Debasis Ganguly and Iadh Ounis for being awarded the Best Paper Award at #ECIR2025 for their work entitled “One size doesn’t fit all: Predicting the number of examples for in-context learning”. The paper will be presented Wednesday morning in Lucca.

Manish Chandra is presenting the #ecir2025 best paper award paper: one size doesn’t fit all: predicting the number of examples for in-context learning w/ Debasis Ganguly Iadh Ounis Glasgow IR Group cc/UofG Computing Science

Slides: gdebasis.github.io/files/ragtalk.… Keep an eye on more exciting work down the line w/ Fangzheng Tian and Craig Macdonald #ecir2025

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

Our #ecir2025 participation is wrapping up. We had a nice time in Lucca. Many thanks to the organisers for hosting us; special thanks to our great collaborator & friend Nicola Tonellotto for his warm hospitality. To reprise the words of Giacomo Puccini “well done!”. See you at Delft!

Glad to share that our paper "The Curious Case of Contexts in Retrieval-Augmented Generation with a Combination of Labelled and Unlabelled Data" will now appear in Wiley Interdisciplinary Reviews journal. Big congratulations to my student Payel Santra et al. Arxiv link and code coming soon.

"All you need are Examples": Exciting results on multi-objective ranking w/o supervised learning by my students Andrew Parry and Nilanjan Sinhababu.

The Road Not Taken Two roads — hard negatives and distillation — diverged in a yellow wood... We looked down the hard negatives one as far as we could... Then took the other — the distillation, as just as fair, And empirically now shown to be the better claim…

First paper - to the best of our knowledge - that links QPP to Agentic RAG.

Really proud to work in close collaboration with this super star colleague of mine...

Glad to discover that our #ECIR2025 best paper award winning work (w/ Manish Chandra and Iadh Ounis) has been taken up as a teaching material in an online Youtube course on LLMs. Glasgow IR Group tinyurl.com/bdhrjxfb

Two papers accepted for the short paper track of #cikm2025. T-Retrievability: A Topic-Focused Approach to Fair Document Exposure in Information Retrieval w/ Xuejun and Zaiqiao Meng HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers w/ Payel Santra et al.