Mandeep Rathee
@rathee_mandeep
Followers
68
Following
975
Media
12
Statuses
64
PhD @l3s_luh Research Center, Hannover Germany
Hannover, Germany
Joined December 2012
We have also released our survey paper, which unifies feedback-based (including Reranker) methods to improve the search, both in Retrieval and RAG tasks. - Test-time Corpus Feedback: From Retrieval to RAG https://t.co/BaPtbfjH86
0
1
2
Happy to see another research group, @haike_xu working in the same direction and our SlideGAR in the BRIGHT world. However, Reranker-Guided Search is not new. There are papers like Quam (WSDM'25), ORE (SIGIR'25), ReFIT(SIGIR'25), TOUR (ACL'23) that use the ranker's guidance.
Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval @haike_xu et al. propose a graph-based search method that strategically selects documents for reranking. π https://t.co/A2Ueb4LqmU π¨π½βπ» https://t.co/Tz6JIhfqoI
2
1
1
@macavaney and I have a PhD studentship with the RAi-funded PROBabLE Futures project to look at responsible usage of LLM-based tools in high-stakes decision-making. Deadline: 30 Sept Details & apply: https://t.co/D9UscAw8An
@responsibleaiuk
@ir_glasgow
@GlasgowCS
findaphd.com
PhD Project - PhD in Computing Science - Responsible Usage of LLM-Based Tooling in High-Stakes Decision-Making at University of Glasgow, listed on FindAPhD.com
0
6
3
π Just wrapped up an incredible experience at #SIGIR2025 in beautiful Padova, Italy! Had the privilege of presenting my research paper and connecting with brilliant minds from the IR community.Β Big thanks to amazing collaborators @vvenki22, @macavaney, and @run4avi
0
1
11
Lucky to work with him.
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 ππ#sigir2025 Cc @GlasgowCS @UofGlasgow @ACMSIGIR
0
0
0
I will present our paper βBreaking the lens of the Telescope: Online Relevance Estimation over Large Retrieval Setsβ at #SIGIR2025 π°οΈ 10:30 AM (16.07.2025) πLocation: GIOTTO (Floor 0) Full Paper: https://t.co/tj1GsJBOyT Slides: https://t.co/fpVMIaDuar
0
6
11
π Thrilled to share that I will 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 @vvenki22 and @run4avi Full paper: https://t.co/LIn2PQrpIj
0
1
8
Had a great time at #ECIR2025! π in Lucca, Italy. I met some amazing researchers. Really enjoyed the company for my all collaborators @vvenki22 , @macavaney and @run4avi. Thanks @vinaysetty for suggesting amazing food places in the city.
1
1
12
After a great banquet last night, now we're enjoying a great presentation from @rathee_mandeep about Guiding Retrieval using Large Language Models! @ir_glasgow @glasgow_cs #ECIR2025
0
4
16
Iβm presenting my paper "Guiding Retrieval using LLM-based Listwise Rankers" at #ECIR2025 this Wednesday! This work is done with @macavaney and @run4avi We explore how LLMs can guide listwise ranking to improve search effectiveness. π Paper: https://t.co/wdFlzsKLRe
0
0
15
SUNAR: Semantic Uncertainty based Neighborhood Aware Retrieval for Complex QA Leverages LLMs to guide Neighborhood Aware Retrieval, dynamically exploring document neighborhoods based on semantic uncertainty. π https://t.co/GO63a830yh π¨π½βπ» https://t.co/SoFZhNCgHb
github.com
Contribute to VenkteshV/SUNAR development by creating an account on GitHub.
0
3
4
At 15:00 on 17th March, Venktesh Viswanathan from TU Delft @tudelft will give an #IRTalk entitled "Bridging Retrieval and Reasoning Gaps for Complex Information Needs". Details: https://t.co/ROB4pwqYaz
@GlasgowCS
@ir_glasgow
0
3
10
It was a great experience to present my work at the Glasgow IR group @ir_glasgow. This talk was based on recently accepted papers -Quam (accepted at #WSDM2025) and SlideGAR (accepted at #ECIR2025) --done in collaboration with Sean MacAvaney @macavaney and Avishek Anand @run4avi
Today, Mandeep Rathee @rathee_mandeep from the L3S Research Center @l3s_luh is giving an #IRTalk entitled "Beyond Bounded Recall: Adaptive Retrieval using Query Affinity Modelling and LLM based Rerankers". Details: https://t.co/2priytqkw2
@GlasgowCS
@ir_glasgow
0
3
13
At 15:00 on 3rd March, Mandeep Rathee @rathee_mandeep from the L3S Research Center @l3s_luh will give an #IRTalk entitled "Beyond Bounded Recall: Adaptive Retrieval using Query Affinity Modelling and LLM based Rerankers". Details: https://t.co/9Pa6fVPAwL
@GlasgowCS
@ir_glasgow
0
3
3
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. π https://t.co/i5X7aScqwc π¨π½βπ» https://t.co/Nke6VSuuyX
github.com
Contribute to Mandeep-Rathee/llmgar development by creating an account on GitHub.
1
10
46
Thrilled to announce that our paper on 'Deep Reinforcement Learning Approach to Configuration Sampling Problem' with my PhD student Amir Abolfazli has won the Best Paper Award at #ICDM2023! π Kudos also to Jakob Spiegelberg, and Greg Palmer @l3s_luh @TUDelft_ai @tudelft
5
3
52