Debasis Ganguly

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

[Debasis Ganguly @debforit]

Why should a simple factoid question and a complex multi-hop question receive identical treatment?

We introduce DRAG, which dynamically chooses the retriever and the generator yielding better answers and/or lower latency.

https://t.co/HtTBLKTGYg
@PayelSantra17 @sbhatia_

[Debasis Ganguly @debforit]

🧵 Excited to share that our paper "Modeling Ranking Properties with In-Context Learning" has been accepted at #EMNLP2026! 🎉

Joint work with @nilanjansb, @MrParryParry, and Pabitra Mitra.

Preprint: https://t.co/XFOtK4aswS

[Debasis Ganguly @debforit]

@nilanjansb @IITKgp 📄 Robustness of IR Models to Collection Growth

Led by PGR Akis Lionis, co-supervised with @macavaney

Collections grow continuously; adding unrelated documents shouldn't hurt effectiveness. But does it?

Finding: IR models suffer some degradation as collections expand. 📚

[Debasis Ganguly @debforit]

🧵 Exciting news from @ir_glasgow: 3 papers from our group have been accepted at #CIKM2026! 🎉

Two long papers and one short paper covering agentic RAG, efficient reranking, and retrieval robustness.

Huge congratulations to the students and collaborators involved! 👏
🧵👇

[Debasis Ganguly @debforit]

📄 Generate to Accelerate: Improved Reranking via LLM-Generated Pivot Documents

Led by external PhD student @nilanjansb (@IITKgp ), primarily supervised by Pabitra Mitra.

What if rerankers could use a document that doesn't even exist? 🤔

[Debasis Ganguly @debforit]

📄 Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generation

Led by PhD student @DanielTian97 , co-supervised with @craig_macdonald .

Can we predict whether the next retrieval step in an agentic RAG pipeline will actually help? 🤖

[Debasis Ganguly @debforit]

To live up to my ISI CS postgraduate roots, I finally wrote a theoretical IR paper 🙂🧮 to estimate how risky is stochastic reranking before we actually apply it? 🎲

Paper: https://t.co/uER5ZtTQN9 (to appear in #ictir2026)
Code: https://t.co/FhwVWHTqdQ

[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