@macavaney profile picture
Sean MacAvaney @macavaney

he/him · Senior Lecturer (Assoc. Professor) at @GlasgowCS @TerrierTeam · working at the intersection of IR&NLP · PhD from @Georgetown IRLab

Joined June 2010
  • Tweets 1,017
  • Following 584
  • Followers 1,870
75 Photos and videos
Pinned Tweet
Sean MacAvaney@macavaney
16 Jul 2025
I'm delighted to have received the SIGIR Early Career Researcher Award! Thanks to all my wonderful students, colleagues, and collaborators for their support and countless discussions about wild new ideas for the field. x.com/ir_glasgow/status/1945…

Glasgow IR Group@ir_glasgow
16 Jul 2025
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
15
2
102
5,192
Sean MacAvaney retweeted
RAGTIME Track 🔎 TREC 2026@trec_ragtime
Jun 2
🚨 Every major AI lab is racing to build better "deep research" agents — systems that search, synthesize, and report across the web. But how do we actually *benchmark* them? Introducing 🧵 TREC RAGTIME — the shared task for rigorous RAG evaluation. trec-ragtime.github.io/

TREC RAGTIME

Official website for the TREC RAGTIME track

trec-ragtime.github.io
1
6
10
1,528
Sean MacAvaney retweeted
Chuan Meng@ChuanMg
Apr 9
Delighted to share that our paper "Revisiting Text Ranking in Deep Research" has been accepted at #SIGIR2026, with @l1tu_0u, @macavaney, and @JeffD We find traditional IR methods remain highly competitive in deep research 📄: arxiv.org/pdf/2602.21456 💻: github.com/ChuanMeng/text-ra…
1
10
105
8,621
Sean MacAvaney retweeted
Craig Macdonald@craig_macdonald
Apr 5
Delighted that our paper “PLAID-PRF — Pseudo-Relevance Feedback with Centroid-like Tokens in PLAID” has been accepted to #sigir2026, w/ Xiao Wang and @macavaney
3
5
51
4,107
Sean MacAvaney retweeted
CLPsych@CLPsychOrg
Jan 21
The call for papers for CLPsych 2026 collocated with ACL 2026 is out and we have a shared task that is accepting applications! We would love to learn more about your amazing work at the intersection of NLP and clinical psychology. clpsych.org/call-for-papers/
4
5
585
Sean MacAvaney retweeted
Craig Macdonald@craig_macdonald
13 Nov 2025
PyTerrier 1.0 has been released: - ➡️ search pipeline validation, visualisation and verification - 📘more documentation - ☕️ java now optional 🆕📰github.com/terrier-org/pyter… Try pip install pyterrier[all] w/ @macavaney
12
22
1,401
Indeed, awesome to see another method leverage rerankers with document proximity to overcome first-stage recall limitations 🤓
Mandeep Rathee@rathee_mandeep
11 Sep 2025
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.
1
10
1,162
Sean MacAvaney retweeted
Mandeep Rathee@rathee_mandeep
15 Jul 2025
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/10.1145/37263… Slides: sigir2025.dei.unipd.it/detai…
4
11
1,042
Sean MacAvaney retweeted
Nicola Tonellotto@ntonellotto
13 Jul 2025
Replying to @joelmmackenzie
@joelmmackenzie kicking off the #SIGIR2025 tutorial on efficient in-memory inverted indexes w/ @macavaney and @antonio_mallia
2
10
691
Sean MacAvaney retweeted
Andreas Chari@andreas_chari
13 Jul 2025
Starting #SIGIR2025 with @macavaney and a tutorial on "Efficient In-Memory Inverted Indexes: Theory and Practice" @ir_glasgow
1
2
19
694
Sean MacAvaney retweeted
Craig Macdonald@craig_macdonald
13 Jul 2025
.@macavaney introducing the Learned Sparse tutorial at #sigir2024
1
1
16
1,686
Sean MacAvaney retweeted
Andrew Parry@MrParryParry
28 May 2025
🚨 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
Sumit@_reachsumit
28 May 2025
Disentangling Locality and Entropy in Ranking Distillation @MrParryParry et al. separate example selection effects from teacher ranking entropy in neural ranking model optimization, showing complex hard-negative pipelines offer minimal gains. 📝arxiv.org/abs/2505.21058
1
9
25
2,044
As @hscells et al say: ♻️ Reduce, Reuse, Recycle! It's never been easier to share indexes (Terrier, Anserini, Pisa, Dense, etc.) using HuggingFace, Zenodo, etc. 🤓
Code example in Python: ``` import pyterrier as pt # load a msmarco-passage index from huggingface index = pt.Artifact.from_hf('macavaney/msmarco-passage.terrier') # it's ready to use! retriever = index.bm25() retriever.search('my dear watson') # qid query docno score rank # 1 my dear watson 5341214 36.087756 0 # 1 my dear watson 2385137 30.109050 1 # ... # share an index to HuggingFace, Zenodo, etc. index = pt.Artifact.load('my-index') index.to_hf('macavaney/my-index') index.to_zenodo() index.to_p2p() ```

ALT Code example in Python: ``` import pyterrier as pt # load a msmarco-passage index from huggingface index = pt.Artifact.from_hf('macavaney/msmarco-passage.terrier') # it's ready to use! retriever = index.bm25() retriever.search('my dear watson') # qid query docno score rank # 1 my dear watson 5341214 36.087756 0 # 1 my dear watson 2385137 30.109050 1 # ... # share an index to HuggingFace, Zenodo, etc. index = pt.Artifact.load('my-index') index.to_hf('macavaney/my-index') index.to_zenodo() index.to_p2p() ```

Sumit@_reachsumit
9 May 2025
Artifact Sharing for Information Retrieval Research @macavaney introduces a flexible way to share artifacts like indices and models for Information Retrieval research, improving both accessibility and usability. 📝arxiv.org/abs/2505.05434 👨🏽‍💻github.com/seanmacavaney/art…
1
4
31
1,945
Sean MacAvaney retweeted
CLPsych@CLPsychOrg
29 Apr 2025
CLPsych 2025 @naaclmeeting is happening soon! We're looking forward to seeing you all. Stay tuned for the Best Poster Award, which will be voted on the day of the workshop after the poster session.
4
11
620
Sean MacAvaney retweeted
RAGTIME Track 🔎 TREC 2026@trec_ragtime
22 Apr 2025
Want to help shape the next generation of RAG systems? TREC RAGTIME focuses on long-form report generation, including sources from multiple languages.
TREC RAGTIME Logo

ALT TREC RAGTIME Logo

1
2
9
940
Eval4RAG kicking off at @ecir2025 with a keynote from @Fabio_Petroni
1
1
30
806
eval4rag.github.io/

Eval4RAG: Workshop on Evaluation of RAG Systems

April 10, 2025 – Co-located at ECIR 2025

eval4rag.github.io
3
317
Sean MacAvaney retweeted
Antonio Mallia@antonio_mallia
8 Apr 2025
It was a really pleasant surprise to learn that our paper “Efficient Constant-Space Multi-Vector Retrieval” aka ConstBERT, co-authored with @macavaney and @ntonellotto received the Best Short Paper Honourable Mention at ECIR 2025! #ECIR2025 #IR #Pinecone
2
8
81
5,289
Sean MacAvaney retweeted
Andreas Chari@andreas_chari
31 Mar 2025
🚨 New Pre-Print!🚨 with @macavaney & @iadh. Stop using "translate-train" for all your multilingual needs. We explore zero-shot transfer for low-resource languages... 🧵
1
5
22
810
We re-annotated DL’19. The results? 👇
Andrew Parry@MrParryParry
3 Mar 2025
🚨 New Pre-Print! 🚨 Reviewer 2 has once again asked for DL’19, what can you say in rebuttal?  We have re-annotated DL’19 in the form of classic evaluation stability studies. Work done with @maik_froebe, @hscells, @fschlatt1, @guglielm0f, @saber_zerhoudi, @macavaney, @EYangTW 🧵
1
29
1,519
Load more