Mandeep Rathee

I will present our paper “Breaking the lens of the Telescope: Online Relevance Estimation over Large Retrieval Sets” at #SIGIR2025
🕰️ 10:30 AM (16.07.2025)
📍Location: GIOTTO (Floor 0)
Full Paper: dl.acm.org/doi/10.1145/...
Slides: sigir2025.dei.unipd.it/detailed-pro...

15.07.2025 22:54 — 👍 2    🔁 0    💬 0    📌 0

🎉 Thrilled to share that I will be presenting our paper SUNAR at #NAACL2025! on May 6, 2025

We introduce a novel approach that leverages LLMs to guide neighborhood-aware retrieval for complex QA.

This work is done with Venktesh and Avishek Anand.

Link to the paper: arxiv.org/pdf/2503.17990

28.04.2025 13:56 — 👍 1    🔁 0    💬 0    📌 0

Had a great time at #ECIR2025! 🎉 in Lucca, Italy. I met some amazing researchers. Really enjoyed the city and Italian food is amazing.

10.04.2025 07:09 — 👍 2    🔁 0    💬 0    📌 0

Excited to share that I’ll be presenting my paper "Guiding Retrieval using LLM-based Listwise Rankers" at #ECIR2025 on this Wednesday!

This work looks at using LLMs to improve retrieval via listwise ranking.

📄 Paper: arxiv.org/pdf/2501.09186
💻 Code: github.com/Mandeep-Rath...

#IR #LLM #ECIR2025

05.04.2025 18:37 — 👍 1    🔁 0    💬 0    📌 0

Guiding Retrieval using LLM-based Listwise Rankers Large Language Models (LLMs) have shown strong promise as rerankers, especially in ``listwise'' settings where an LLM is prompted to rerank several search results at once. However, this ``cascading'' ...

Guiding Retrieval using LLM-based Listwise Rankers

Introduces a method to integrate listwise LLM rerankers into adaptive retrieval, improving nDCG@10 by up to 13.23% and recall by 28.02% while maintaining efficiency.

📝 arxiv.org/abs/2501.09186
👨🏽‍💻 github.com/Mandeep-Rath...

17.01.2025 03:07 — 👍 1    🔁 1    💬 0    📌 0