Debasis Ganguly
@debforit
Lecturer/Asst. Professor at the School of Computing, University of Glasgow (@UofGlasgow/@GlasgowCS/@IDAglasgow/@ir_glasgow)
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 @ntonellotto for his warm hospitality. To reprise the words of Giacomo Puccini “well done!”. See you at Delft!
Looking fwd to my talk on 10th @ecir2025, where I'll be giving a perspective on the potentials of applying #QPP to improve #RAG.
📢 The final schedule for the Query Performance Prediction (QPP++ 2025) Workshop at @ecir2025 is now live! 📅 Join us on 10th April 2025: qppworkshop.github.io 🎤 Keynote by @debforit : "The Role of Query Performance Prediction in Developing Adaptive Search and RAG Systems"
Glad to discover that our #ECIR2025 best paper award winning work (w/ Manish Chandra and @iadh) has been taken up as a teaching material in an online Youtube course on LLMs. @ir_glasgow tinyurl.com/bdhrjxfb
Really proud to work in close collaboration with this super star colleague of mine...
Huge congratulations to @macavaney on receiving the prestigious ACM SIGIR Early Career Researcher Award in the research category! This well-deserved recognition highlights the excellence & impact of his work in the IR community 👏🎉#sigir2025 Cc @GlasgowCS @UofGlasgow @ACMSIGIR
First paper - to the best of our knowledge - that links QPP to Agentic RAG.
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/ @JinyuanF @debforit @mengzaiqiao @craig_macdonald
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…
🚨 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 @debforit and @macavaney, we explore data selection in modern ranking. 🧵 Below
"All you need are Examples": Exciting results on multi-objective ranking w/o supervised learning by my students @MrParryParry and @nilanjansb.
🚨 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 @nilanjansb from IIT Kharagpur and @debforit. 🧵 Below!
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 @WIREs_Reviews journal. Big congratulations to my student @PayelSantra17 et al. Arxiv link and code coming soon.
Happy to share some of the ongoing work of @DanielTian97 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 @ir_glasgow
@debforit is giving keynote talk about QPP’s application in LLM era at the QPP++ workshop #ecir2025 @ir_glasgow
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/ @MrParryParry & Manish Chandra. Slides: tinyurl.com/4t23dj2y
Back to back speakers from Glasgow in the QPP++ workshop at #ECIR2025, with lots of other interesting talks coming up. @DanielTian97 is presenting his work (w/ @craig_macdonald & @debforit) that revisits query variants for QPP. Great stuff! @ir_glasgow @glasgowcs #ECIR2025
Slides: gdebasis.github.io/files/ragtalk.… Keep an eye on more exciting work down the line w/ @DanielTian97 and @craig_macdonald #ecir2025
Keynote presentation by @debforit in the QPP++ workshop at #ecir2025 Cc/ @ir_glasgow
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/ @debforit @iadh @ir_glasgow cc/@GlasgowCS
Congratulations to Manish Chandra @debforit and @iadh 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.
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.
Glad to share that "Exploring the Role of Diversity in Example Selection for In-Context Learning" w/ @JanakKapuriya, @kaushik_manit, and @sbhatia_ has been accepted as a short paper in #SIGIR2025. Arxiv and git link coming soon.
More incredible @ir_glasgow contributions today at @ecir2025 with @DanielTian97 now presenting his work with @debforit and @craig_macdonald. #ecir2025
Now @danieltian97 is presenting our work on relevance propagated from retriever to generator in RAG w/ @debforit @ir_glasgow #ecir2025
A large contingent of our staff & students @GlasgowCS will soon be traveling to #ECIR2025. We'll be presenting our latest work in #search & #RecSys throughout the 5-day conference. Looking forward to connecting with colleagues and friends in Lucca! @ecir2025 @IDAglasgow