
Craig Macdonald
@craig_macdonald
Professor of Information Retrieval
ID: 59504716
http://www.dcs.gla.ac.uk/~craigm/ 23-07-2009 15:59:58
2,2K Tweet
2,2K Followers
394 Following

Great news from #SIGIR2025 â our (/w Craig Macdonald and Nicola Tonellotto) full paper âEfficient Recommendation with Millions of Items by Dynamic Pruning of Sub-Item Embeddingsâ has been accepted. Nice timing too: all co-authors are now at ECIR, so we get to celebrate together.

Watching Jack McKechnie present our work on context selection for LLM evaluation w/ graham mcdonald #ecir2025


Now Fangzheng Tian is presenting our work on relevance propagated from retriever to generator in RAG w/ Debasis Ganguly Glasgow IR Group #ecir2025


Now Ariane MĂźller is giving a talk about analysing semantic matching in ColBERT. Very interesting stuff, go check out the poster later on! ECIR2025 Glasgow IR Group UofG Computing Science #ECIR2025



Congratulations to Manish Chandra Debasis Ganguly and Iadh Ounis for being awarded the Best Paper Award at #ECIR2025 for their work entitled âOne size doesnât fit all: Predicting the number of examples for in-context learningâ. The paper will be presented Wednesday morning in Lucca.


Manish Chandra is presenting the #ecir2025 best paper award paper: one size doesnât fit all: predicting the number of examples for in-context learning w/ Debasis Ganguly Iadh Ounis Glasgow IR Group cc/UofG Computing Science


In the #ecir2025 QPP+ workshop, Fangzheng Tian is presenting our work on revisitingquery variants for QPP w/ Debasis Ganguly cc/ Glasgow IR Group


Keynote presentation by Debasis Ganguly in the QPP++ workshop at #ecir2025 Cc/ Glasgow IR Group


. Sean MacAvaney and I just talked about caching and precomputation in PyTerrier declarative experiments in the #ecir2025 OpenWebSearch workshop cc/ Glasgow IR Group


.Andreas Chari talking about fine tuning dense retrieval models for low resource languages #ecir2025. Work with Sean MacAvaney and Iadh Ounis cc/ Glasgow IR Group



As Harry Scells et al say: âťď¸ Reduce, Reuse, Recycle! It's never been easier to share indexes (Terrier, Anserini, Pisa, Dense, etc.) using HuggingFace, Zenodo, etc. đ¤


.@sharepoint any update on when we can copy from a PDF? same on Microsoft Teams... answers.microsoft.com/en-us/msteams/âŚ

đ Glad to share that our paper "KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation" (w/ Zaiqiao Meng and Craig Macdonald) has been accepted at #ACL2025 as a main conference paper!


Delighted that Aleksandr V. Petrov passed his đ PhD defense this morning, without corrections. Thanks to Pablo Castells and Nicolas Pugeault for their thorough examination of the thesis, and Mireilla Bikanga Ada for convening the defense!


âWhich retrieval library should you use for RAG? Which agent library? Where do you get datasets? We made PyTerrier RAG to stop your headaches! Led by Craig Macdonald /w (Jinyuan Fang , me and Zaiqiao Meng )! đ§ľ âŹď¸
