🎄 PyTerrier Advent 25/25: To wrap up the our advent series, we'd like thank the contributors shown below, and to the many others who support the PyTerrier ecosystem! #WorldChangersTogether

🎄 PyTerrier Advent 24/25: Removing low-quality docs can boost search quality and cut indexing costs. Our SIGIR’24 paper QT5 trains a T5 model to filter passages at indexing time—easy to integrate, and works with dense, PISA, or SPLADE indexes too.

🎄PyTerrier Advent 23/25: You’ve done retrieval, but the results seem too homogeneous. Use a diversification reranker. Shown below is the implicit MMR diversification approach, instantiated on a BM25 or dense retrieval, but even an explicit approach like xQuAD (c.f. Rodrygo Santos) is easy to write.

🎄 PyTerrier Advent 22/25: A more complex pipeline—knowledge-graph–enhanced RAG from our EMNLP 2024 paper TRACE. We build a KG over retrieved docs, then use a transformer to reason over triples for better QA. This pipeline instantiation uses a cache (see 20th advent) on LLM-based KG extraction.

🎄PyTerrier Advent 21/25: Bounded recall blues got you down? You can use Adaptive Retrieval techniques, like GAR, LADR, and LAFF, to efficiently surface missing relevant documents.

🎄PyTerrier Advent 20/25: You can think of every PyTerrier transformer as a function - mapping from one dataframe type to another. This makes them easily cachable, courtesy of pyterrier_caching. We have cache object for retrievers, rerankers, or even indexing-time transformations (e.g. Doc2Query)

🎄 PyTerrier Advent 19/25: PyTerrier-RAG brings agentic RAG to your workflows with support for SOTA methods like Search-R1 and R1-Searcher, to combine retrievers and reasoning. You could even swap BM25 out for dense or LSR retriever.

🎄 PyTerrier Advent 18/25: In RAG, the reader runs the LLM—but your pipeline shouldn’t depend on the LLM stack. PyTerrier-RAG separates Reader from Backend, letting you swap vLLM ↔ HF with one line while keeping the same pipeline (and even share a Backend with other stages).

🎄 PyTerrier Advent 17/25: FlexIndex simplifies dense retrieval by supporting FAISS, Voyager, FlatNav & more. It auto-builds data structures, reuses vector stores to cut storage costs, and offers one familiar API for many retrievers.

🎄PyTerrier Advent 16/25: Speaking of Learned Sparse Retrieval, PyTerrier has bindings to two backend search engines that provide blazing-fast retrieval over sparse vectors: PISA and BMP. You can see that we really work to keep the look-and-feel uniform between implementations

🎄PyTerrier Advent 15/25: A very well-known learned sparse method is SPLADE. Our pyt_splade plugin makes it easy to use SPLADE by formulating Terrier indexing & retrieving pipelines that are composed with a SPLADE encoder, adding extra columns (e.g. query_toks). Try it 👉 github.com/cmacdonald/p...

🎄 PyTerrier Advent 14/25: So we’ve seen sparse and dense retrieval in PyTerrier. Some folk recommend hybrid retrieval – e.g. reciprocal rank fusion (RRF) of sparse and dense results. We have an easy pipeline component that combine two sets of results by RRF (w/ a pretty schematic by Sean MacAvaney)

🎄 PyTerrier Advent 10/25: Dense retrieval often improves with pseudo-relevance feedback (Rocchio-style). In PyTerrier_DR it’s easy: encode query, retrieve docs, a transformer to mix doc vectors w/ the query vector, and then re-retrieve. pyterrier.readthedocs.io/en/latest/ex...

🎄 PyTerrier Advent 13/25: Doc2query expands docs with generated queries, but can hallucinate. Our ECIR’23 paper Doc2query-- (aka "minus minus") filters generated queries using a cross-encoder before indexing. PyTerrier pipeline: generate→score→filter→index. 📄https://arxiv.org/pdf/2301.03266

🎄 PyTerrier Advent 12/25: Beyond dense retrieval, learned sparse methods like Doc2Query expand docs with predicted queries before indexing. Our pyterrier_doc2query plugin makes this easy for any corpus—perfectly intuitive as PyTerrier’s pipelines can be applied at indexing time too!

🎄PyTerrier Advent 11/25: Want to use an external search services with PyTerrier? No problemo! It has integrations with APIs for Semantic Scholar, ChatNoir (thanks to Jan Heinrich Merker!), Pinecone, and others!

🎄 PyTerrier Advent 10/25: Dense retrieval often improves with pseudo-relevance feedback (Rocchio-style). In PyTerrier_DR it’s easy: encode query, retrieve docs, a transformer to mix doc vectors w/ the query vector, and then re-retrieve. pyterrier.readthedocs.io/en/latest/ex...

🎄PyTerrier Advent 9/25: Yesterday—dense retrieval with E5 via PyTerrier_DR. Today—RAG! PyTerrier_RAG readers generate answers from retrieved docs. Example: a FiD reader over E5 results, w/ & w/o monoT5 reranking 👇 Check the full notebook to see impact on answer quality. github.com/terrierteam/...

🎄PyTerrier Advent 8/25: Beyond sparse! PyTerrier_dr adds dense indexing & retrieval. Instantiate an encoder model, compose with FlexIndex. Retrieval is identical. Support models include: ANCE, TCT-ColBERT, BGE, E5, or any SentenceTransformer model. 👉 github.com/terrierteam/...

🎄PyTerrier Advent 6/25: Lets see some more neural rerankers: MonoT5 & DuoT5 (DuoT5 is a more costly pairwise reranker). We use PyTerrier's succinct rank cutoff operator (%) to cut the nbr of retrieved docs reranked by each of the MonoT5 & DuoT5 stages. Try it out: github.com/terrierteam/...

🎄PyTerrier Advent 5/25: Comparing pipelines (e.g., BM25 vs RM3)? Use pt.Experiment(baseline=…) to see MAP gains/losses per query and paired t-test p-values. Multiple-test corrections are supported too. 📄https://pyterrier.readthedocs.io/en/latest/experiments.html#significance-testing

Paper alert 🚨"Investors Are (Not) Always Right: A Comparison of Transaction-Based and Profitability-Based Metrics for Financial Asset Recommendations", with @richardmcc.bsky.social, Nikos Droukas, @craigmacdonald.bsky.social & @iadhounis.bsky.social has been accepted at ACM TOIS! 🧵(1/5)

PyTerrier, a software platform developed at @uofgcompsci.bsky.social which helps facilitate the development of AI-powered search engines, has won a national award from @wearebcs.bsky.social! Read more here: www.gla.ac.uk/news/headlin...

🎄We want to try something new and fun this year – an “Advent Calendar” of PyTerrier pipelines 🤓 We’ll kick it off with *the* baseline: BM25 on MSMARCO. One line to download a pre-built index, one line to make a BM25 retriever, one line to search.

We are happy to sponsor the Keith Van Rijsbergen (KvR) Award at #ECIR2026 📢 𝗡𝗼𝗺𝗶𝗻𝗮𝘁𝗶𝗼𝗻𝘀 𝗮𝗿𝗲 𝗻𝗼𝘄 𝗼𝗽𝗲𝗻! Details and Submission Form at @ecir2026.eu website: lnkd.in/emecdsXm 🗓 𝗗𝗲𝗮𝗱𝗹𝗶𝗻𝗲: 𝟭𝟱 𝗝𝗮𝗻𝘂𝗮𝗿𝘆 𝟮𝟬𝟮𝟲 www.linkedin.com/posts/glasgo...

The brilliant @annarezk.bsky.social from @uofglasgow.bsky.social presenting on stakeholder research as part of the RAI funded Participatory Auditing Harm Workbenches and Methodologies project at the #RAIAHM in Manchester. Innovative and significant work #PHAWM #RAI2025 #AIAuditing

We’re hiring a 2nd RA/PDRA at @uofgcompsci.bsky.social for the EU CLIMINVEST Project! Work with @iadhounis.bsky.social, @craigmacdonald.bsky.social & Richard McCreadie on LLM-powered AI agents for ESG & risk assessment in green investment. Apply by Dec 15: www.linkedin.com/posts/iadhou...

📢 We're also now on LinkedIn! Follow the Glasgow Information Retrieval Group for updates on IR research, @irglasgow.bsky.social activities, events, and collaborations: 🔗 linkedin.com/company/glasgow-information-retrieval-group #InformationRetrieval #IR #AI #recsys #RecommenderSystems #Glasgow

📢 We're off to #SIGIR2025 in Padova! A large contingent of our students & staff will be at the main conference + tutorials, workshops & #ICTIR2025. Let’s connect if you’re around! 🤝 Also: we're hiring in #FinTech — DM us if you're interested! #IR #Hiring #Research #ACMSIGIR

🎉 An open-source AI Agent project, EvoAgentX, led by @uofglasgow.bsky.social PhD students, has received 260+ ⭐️ on GitHub in just 5 DAYS!🔥 🤖 The project aims to build a Self-Evolving Ecosystem of AI Agents. @irglasgow.bsky.social @idaglasgow.bsky.social #AI #EvoAgentX

Huge congratulations to our brilliant PhD graduates: @tjaenich.bsky.social, @mariavlachou.bsky.social, and @apetrov.bsky.social 🎉 It’s been a joy having you @uofgcompsci.bsky.social - We’re so proud of all you’ve achieved and can’t wait to see what amazing things you’ll do next! 👏 #PhDGraduation

Congratulations to @tjaenich.bsky.social who defended his PhD Thesis Fair Group-Based Exposure of Documents in Ranked Search Results 👏👏 Was a pleasure supervising your PhD along with @iadhounis.bsky.social. @irglasgow.bsky.social Thanks to the examiners Dr. Sole Pera and Christos Anagnostopoulos!

Arrivederci #ecir2025 … and thanks for all the fish - see you all in Delft!

Congratulations to Manish Chandra, @gdebasis.bsky.social and @iadhounis.bsky.social for being awarded the Best Paper Award at #ECIR2025 for their work entitled “One size doesn’t fit all: Predicting the number of examples for in-context learning”. The paper will be presented Wednesday morning.

Yesterday, @ttsamurai.bsky.social has been busy at #ECIR2025, demoing FinPersona (w/ M Suzuki l, K Izumi, @javiersanzcruza.bsky.social, @richardmcc.bsky.social & @iadhounis.bsky.social). Great to see many people interested in FinTech LLM agents! Try Demo at: huggingface.co/spaces/TTsam...

Happy to share that our (w/ @grahammcdonald.bsky.social and @craigmacdonald.bsky.social) work "Measuring Hypothesis Testing Errors in the Evaluation of Retrieval Systems" has been accepted to #SIGIR2025 as a short paper! 🎉Exciting times! 🇮🇹 @ir_glasgow

A large contingent of our staff & students @uofgcompsci.bsky.social will soon be traveling to #ECIR2025. We'll be presenting our latest work in #search & #RecSys throughout the 5-day conference. Looking forward to connecting with colleagues and friends in Lucca!

About a week left to apply to this postdoctoral position in Responsible AI/IR at @irglasgow.bsky.social Details are below. Deadline to apply: 26th March

Watching @iadhounis.bsky.social give a Keynote talk about reproducibility and PyTerrier pipelines in Tsukuba x Glasgow workshop on the Frontiers of AI. @irglasgow.bsky.social

We are recruiting a postdoc at @irglasgow.bsky.social to work on the Participatory Harm Auditing Workbenches and Methodologies (PHAWM) RAI UK project on Responsible AI. phawm.org Deadline: 26th March www.jobs.gla.ac.uk/job/research...

Come work with us in Glasgow! We are recruiting a postdoc at @uofgcompsci.bsky.social to work on understanding & measuring the harm of AI-driven IR approaches within various search contexts as part of the PHAWM project on Responsible AI. Deadline: 26/03 Details: www.jobs.gla.ac.uk/job/research...

Happy to share that our paper entitled "A Multi-modal Large Language Model with Graph-of-Thought for Effective Recommendation" has been accepted by @naaclmeeting.bsky.social as a main conference paper, co-authored with @iadhounis.bsky.social. #NAACL2025

We have 2 tenure-track faculty openings in Machine Learning at @uofgcompsci.bsky.social; Applications are welcome in the general areas of AI & ML, which complement existing strengths in the @idaglasgow.bsky.social section. Details at: jobs.gla.ac.uk/job/lecturer-s… Deadline: 17 Feb 2025 at 23:45

Happy to share that our paper entitled “Enhancing Recommender Systems: Deep Modality Alignment with Large Multi-Modal Encoders” has been accepted by ACM Transactions on Recommender Systems - joint work with Zijun Long, @iadhounis.bsky.social, @craigmacdonald.bsky.social and @richardmcc.bsky.social.

At 15:00 on 13th January, Francesco Luigi De Faveri from University of Padua will give an #IRTalk entitled "Preserving Privacy in Information Retrieval: Leveraging Differential Privacy Across Domains". Details: samoa.dcs.gla.ac.uk/events/viewt... @uofgcompsci.bsky.social @irglasgow.bsky.social

🚨A week to go (!) before the poster papers abstract deadline for #ICDCS2025🚨 Submissions should be in the form of papers in a short format that are best presented as posters. icdcs2025.icdcs.org/call-for-pos... Deadlines: 15 Jan (abstracts), 22 Jan (papers).

Today, Xiaoyu Zhang from Shandong University is giving an #IRTalk entitled "Enhancing Conversational Recommender Systems: Integrating Knowledge, Context, and Emotions". Details: samoa.dcs.gla.ac.uk/events/viewt... @uofgcompsci.bsky.social @irglasgow.bsky.social

At 15:00 on 6th January, Xiaoyu Zhang from Shandong University will give an #IRTalk entitled "Enhancing Conversational Recommender Systems: Integrating Knowledge, Context, and Emotions". Details: samoa.dcs.gla.ac.uk/events/viewt... @uofgcompsci.bsky.social @irglasgow.bsky.social

We snuck out new releases in PyTerrier ecosystem in the last few weeks, with a number of 😍 changes…. 🧵👇 1/7 github.com/terrier-org/... pyterrier.readthedocs.io cc/ @irglasgow.bsky.social

Glad to share that our work (by Fanghzhen Tian and w/ @gdebasis.bsky.social and myself) "Is Relevance ‘Lost in Transmission’ from Retriever to Generator?" has been accepted to #ecir2025 as a full paper. See you next spring in Lucca 🙋🏻‍♂️ @irglasgow.bsky.social