Debasis Ganguly

Lecturer/Asst. Professor at the School of Computing, University of Glasgow (@UofGlasgow/@GlasgowCS/@IDAglasgow/@ir_glasgow)

[Debasis Ganguly @debforit]

A single-authored paper always feels special, perhaps even more so these days, when most of my research time is devoted to working with students.
Delighted to share that my paper, “A Theoretical Framework for Risk Analysis of Stochastic Rankers,” has been accepted at #ictir2026.

[Debasis Ganguly @debforit]

While IR4RAG is more common, the other way is cool as well. Check out this excellent work on RAG4IR by one of my grad students. #tois #rag #qpp

[Fangzheng Tian @DanielTian97]

I am pleased to share that our journal article, "RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation," has been accepted by ACM Transactions on Information Systems (TOIS), a joint work with @debforit and @craig_macdonald.

[Debasis Ganguly @debforit]

@DanielTian97 @craig_macdonald @PayelSantra17 🚀📈 Does QPP actually improve IR?
The first comparative study showing that QPP can improve retrieval effectiveness by selecting variable proportions of information across rankers.
📄 Preprint: https://t.co/5qwmD9Z0dD
🧠💬 Stay tuned for the talks at #ECIR2026, feedback welcome!

[Debasis Ganguly @debforit]

🧵📢 Preprints out!
Ahead of ECIR’26 #ecir2026, I’m excited to share three new papers on Query Performance Prediction (QPP) — continuing my long-standing obsession with understanding when retrieval works (and when it doesn’t).
More info⬇️

[Debasis Ganguly @debforit]

@DanielTian97 @craig_macdonald ⚖️🤖 QPP beyond single rankers
How well do existing QPP models perform on a harder and more meaningful task?

➡️ Comparing multiple rankers for the same query — not just predicting absolute performance.

📄 Preprint: https://t.co/ewthRhtlSV
@PayelSantra17

[Debasis Ganguly @debforit]

Glad to share that our paper w/ @DanielTian97 (grad student) and @craig_macdonald "Predicting Retrieval Utility and Answer Quality in Retrieval-Augmented Generation" got accepted in #Ecir2026.
TLDR; the paper extends QPP to RAG for QA downstream task. @ir_glasgow

[Debasis Ganguly @debforit]

Joemon from University of Glasgow introduced by Jaap before his #fire2025 talk on conflict mining on social media.
@ir_glasgow @fire_forum

[Debasis Ganguly @debforit]

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 @mengzaiqiao
HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers w/ @PayelSantra17 et al.

[Debasis Ganguly @debforit]

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

https://t.co/f51lHbLTql

[Debasis Ganguly @debforit]

missed to tag: @JinyuanF and @mengzaiqiao

[Debasis Ganguly @debforit]

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 @DanielTian97

[Debasis Ganguly @debforit]

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

[Glasgow IR Group @ir_glasgow]

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

[Debasis Ganguly @debforit]

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

[Fangzheng Tian @DanielTian97]

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: https://t.co/FPBEFQbuu5. #SIGIR2025 cc/ @JinyuanF @debforit
@mengzaiqiao @craig_macdonald

[Debasis Ganguly @debforit]

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…

[Andrew Parry @MrParryParry]

🚨 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

[Debasis Ganguly @debforit]

"All you need are Examples": Exciting results on multi-objective ranking w/o supervised learning by my students @MrParryParry and @nilanjansb.

[Andrew Parry @MrParryParry]

🚨 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!

[Debasis Ganguly @debforit]

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.

[Glasgow IR Group @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!

[Debasis Ganguly @debforit]

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: https://t.co/MkCriG44ly
#ecir2025 @ir_glasgow

[Fangzheng Tian @DanielTian97]

@debforit is giving keynote talk about QPP’s application in LLM era at the QPP++ workshop #ecir2025 @ir_glasgow

[Debasis Ganguly @debforit]

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 https://t.co/7GRLR4ZNUj w/ @MrParryParry & Manish Chandra.
Slides: https://t.co/FfxnytjIbl

[Jack McKechnie @JackMcK1999]

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