His work focuses on #InformationRetrieval and #RAG, with a particular interest in System 1 models as zero-shot rerankers and in parametric RAG, which represents information as weight updates.
Outside of research, he enjoys gardening 🌱, pumpfoiling 🏄♂️, and hiking 🥾.
Outside of research, he enjoys gardening 🌱, pumpfoiling 🏄♂️, and hiking 🥾.
November 6, 2026 at 1:00 PM
His work focuses on #InformationRetrieval and #RAG, with a particular interest in System 1 models as zero-shot rerankers and in parametric RAG, which represents information as weight updates.
Outside of research, he enjoys gardening 🌱, pumpfoiling 🏄♂️, and hiking 🥾.
Outside of research, he enjoys gardening 🌱, pumpfoiling 🏄♂️, and hiking 🥾.
A RAG chunk doesn't know which document it came from.
Second post on our Baltic DB&IS 2026 paper: contextual enrichment. Before embedding, an LLM writes 50–100 tokens of document context for each chunk.
#LLM #RAG #InformationRetrieval
Second post on our Baltic DB&IS 2026 paper: contextual enrichment. Before embedding, an LLM writes 50–100 tokens of document context for each chunk.
#LLM #RAG #InformationRetrieval
November 3, 2026 at 12:28 PM
A RAG chunk doesn't know which document it came from.
Second post on our Baltic DB&IS 2026 paper: contextual enrichment. Before embedding, an LLM writes 50–100 tokens of document context for each chunk.
#LLM #RAG #InformationRetrieval
Second post on our Baltic DB&IS 2026 paper: contextual enrichment. Before embedding, an LLM writes 50–100 tokens of document context for each chunk.
#LLM #RAG #InformationRetrieval
University College Dublin is recruiting a postdoctoral research fellow in information retrieval and natural language processing.
mlscientist.com/ucd-postdoct... #informationretrieval
mlscientist.com/ucd-postdoct... #informationretrieval
November 2, 2026 at 1:51 PM
University College Dublin is recruiting a postdoctoral research fellow in information retrieval and natural language processing.
mlscientist.com/ucd-postdoct... #informationretrieval
mlscientist.com/ucd-postdoct... #informationretrieval
Phase 13, Semantic Search and Retrieval, is done. Counting words 0.026, BM25 0.382, embedding 0.340, fused 0.395 (p 0.18). With the answers hidden, the top score barely moved: AUC 0.599. #MT24Learning #InformationRetrieval #RAG
October 29, 2026 at 10:50 PM
Phase 13, Semantic Search and Retrieval, is done. Counting words 0.026, BM25 0.382, embedding 0.340, fused 0.395 (p 0.18). With the answers hidden, the top score barely moved: AUC 0.599. #MT24Learning #InformationRetrieval #RAG
Search by meaning vs keywords on 225 judged questions: WordLlama 0.340, BM25 0.382 nDCG@10 (p 0.0012). Rank fusion 0.395, p 0.18. BM25 + GloVe fell to 0.258. #MT24Learning #SemanticSearch #InformationRetrieval
October 27, 2026 at 9:49 PM
Search by meaning vs keywords on 225 judged questions: WordLlama 0.340, BM25 0.382 nDCG@10 (p 0.0012). Rank fusion 0.395, p 0.18. BM25 + GloVe fell to 0.258. #MT24Learning #SemanticSearch #InformationRetrieval
RAG's retriever on 225 judged questions: a judged passage in the top 5 for 0.769; 52 get none. Hide every right paper: the top score barely drops (AUC 0.599); a floor keeping 90% lets 84% through. #MT24Learning #RAG #InformationRetrieval
October 28, 2026 at 8:20 PM
RAG's retriever on 225 judged questions: a judged passage in the top 5 for 0.769; 52 get none. Hide every right paper: the top score barely drops (AUC 0.599); a floor keeping 90% lets 84% through. #MT24Learning #RAG #InformationRetrieval
Built BM25 from an inverted index on the Cranfield set (1,400 abstracts, 225 judged questions). Counting matched words: 0.026 nDCG@10. BM25: 0.382. Matching questions by the file's own IDs: 0.010. #MT24Learning #InformationRetrieval #SearchEngines
October 27, 2026 at 1:40 AM
Built BM25 from an inverted index on the Cranfield set (1,400 abstracts, 225 judged questions). Counting matched words: 0.026 nDCG@10. BM25: 0.382. Matching questions by the file's own IDs: 0.010. #MT24Learning #InformationRetrieval #SearchEngines
LIME-Rec, a non-autoregressive recommender approach using sequential, collaborative, and offline semantic signals, is proposed as an alternative to serving-time LM inference, achieving top reported means…
#RecommenderSystems #LanguageModels #InformationRetrieval
https://arxiv.org/abs/2608.01260
#RecommenderSystems #LanguageModels #InformationRetrieval
https://arxiv.org/abs/2608.01260
October 20, 2026 at 8:02 AM
LIME-Rec, a non-autoregressive recommender approach using sequential, collaborative, and offline semantic signals, is proposed as an alternative to serving-time LM inference, achieving top reported means…
#RecommenderSystems #LanguageModels #InformationRetrieval
https://arxiv.org/abs/2608.01260
#RecommenderSystems #LanguageModels #InformationRetrieval
https://arxiv.org/abs/2608.01260
A new RAG approach for EDA documentation groups related artifacts into functional units and trains an encoder to align queries with them, combining unit and chunk retrieval to handle scattered, tightly coupled technical…
#RAG #EDADocs #DocQA #InformationRetrieval
https://arxiv.org/abs/2610.09361
#RAG #EDADocs #DocQA #InformationRetrieval
https://arxiv.org/abs/2610.09361
October 8, 2026 at 12:01 PM
A new RAG approach for EDA documentation groups related artifacts into functional units and trains an encoder to align queries with them, combining unit and chunk retrieval to handle scattered, tightly coupled technical…
#RAG #EDADocs #DocQA #InformationRetrieval
https://arxiv.org/abs/2610.09361
#RAG #EDADocs #DocQA #InformationRetrieval
https://arxiv.org/abs/2610.09361
MDKeyChunker asks whether one LLM call per chunk for metadata beats Markdown's free structure in RAG retrieval, testing it with qwen2.5:7b across BM25, dense, and hybrid setups on Qasper and FreshStack datasets. The…
#RAG #Markdown #LLM #InformationRetrieval
https://arxiv.org/abs/2603.23533
#RAG #Markdown #LLM #InformationRetrieval
https://arxiv.org/abs/2603.23533
October 7, 2026 at 4:01 PM
MDKeyChunker asks whether one LLM call per chunk for metadata beats Markdown's free structure in RAG retrieval, testing it with qwen2.5:7b across BM25, dense, and hybrid setups on Qasper and FreshStack datasets. The…
#RAG #Markdown #LLM #InformationRetrieval
https://arxiv.org/abs/2603.23533
#RAG #Markdown #LLM #InformationRetrieval
https://arxiv.org/abs/2603.23533
A new benchmark, ScholarCatalyst, uses annotations from 184 lead authors across 207 CS papers to evaluate how well AI agents retrieve prior work that inspired completed research projects. The task tests…
#OpenSourceAI #AIResearch #InformationRetrieval #Benchmarking
https://arxiv.org/abs/2610.02202
#OpenSourceAI #AIResearch #InformationRetrieval #Benchmarking
https://arxiv.org/abs/2610.02202
October 3, 2026 at 12:01 AM
A new benchmark, ScholarCatalyst, uses annotations from 184 lead authors across 207 CS papers to evaluate how well AI agents retrieve prior work that inspired completed research projects. The task tests…
#OpenSourceAI #AIResearch #InformationRetrieval #Benchmarking
https://arxiv.org/abs/2610.02202
#OpenSourceAI #AIResearch #InformationRetrieval #Benchmarking
https://arxiv.org/abs/2610.02202
Your RAG score needs its test set attached.
Pharos Production's RAG delivery includes retrieval evaluation sets. Ask for the query-set version and corpus snapshot behind the score.
pharosproduction.com
#RAG #AIEvaluation #InformationRetrieval
Pharos Production's RAG delivery includes retrieval evaluation sets. Ask for the query-set version and corpus snapshot behind the score.
pharosproduction.com
#RAG #AIEvaluation #InformationRetrieval
Software Development Company | Pharos Production
Custom software development company since 2013 • 90+ engineers • 110+ apps for FinTech, healthcare and Web3 • Rated 5/5 on Clutch • Free estimate
pharosproduction.com
September 23, 2026 at 7:23 AM
Your RAG score needs its test set attached.
Pharos Production's RAG delivery includes retrieval evaluation sets. Ask for the query-set version and corpus snapshot behind the score.
pharosproduction.com
#RAG #AIEvaluation #InformationRetrieval
Pharos Production's RAG delivery includes retrieval evaluation sets. Ask for the query-set version and corpus snapshot behind the score.
pharosproduction.com
#RAG #AIEvaluation #InformationRetrieval
Keep versioned labels and failed queries. Define the metric and cutoff so reviewers can trace each result to retrieved evidence.
Deliverables: pharosengineeringnotes.wordpress.com/2026/09/18/r...
#RAG #AIEvaluation #InformationRetrieval
Deliverables: pharosengineeringnotes.wordpress.com/2026/09/18/r...
#RAG #AIEvaluation #InformationRetrieval
How to Specify Retrieval Evaluation Deliverables for a RAG Vendor
Specify a RAG vendor evaluation package with labeled-data ownership, query-level evidence, metric definitions and an eight-part acceptance matrix.
pharosengineeringnotes.wordpress.com
September 23, 2026 at 7:23 AM
Keep versioned labels and failed queries. Define the metric and cutoff so reviewers can trace each result to retrieved evidence.
Deliverables: pharosengineeringnotes.wordpress.com/2026/09/18/r...
#RAG #AIEvaluation #InformationRetrieval
Deliverables: pharosengineeringnotes.wordpress.com/2026/09/18/r...
#RAG #AIEvaluation #InformationRetrieval
CLEF'26 starting in Jena!
Will be great to see all the tasks people have been working on over the year. I'm sure there will be plenty of inspiration for new visions for the future of IR -> desires-conf.org/2027/
#CLEF2026 #InformationRetrieval #NLP
#DESIRES2027
Will be great to see all the tasks people have been working on over the year. I'm sure there will be plenty of inspiration for new visions for the future of IR -> desires-conf.org/2027/
#CLEF2026 #InformationRetrieval #NLP
#DESIRES2027
DESIRES 2027 – Cologne, Germany
The conference for discussing visionary ideas in search and retrieval systems
desires-conf.org
September 21, 2026 at 7:44 AM
CLEF'26 starting in Jena!
Will be great to see all the tasks people have been working on over the year. I'm sure there will be plenty of inspiration for new visions for the future of IR -> desires-conf.org/2027/
#CLEF2026 #InformationRetrieval #NLP
#DESIRES2027
Will be great to see all the tasks people have been working on over the year. I'm sure there will be plenty of inspiration for new visions for the future of IR -> desires-conf.org/2027/
#CLEF2026 #InformationRetrieval #NLP
#DESIRES2027
Explaining retrieval-augmented generation #AI #MachineLearning #NaturalLanguageProcessing #RAG #InformationRetrieval
Explaining retrieval-augmented generation
Retrieval-augmented generation (RAG) makes a language model fetch documents before it answers. How the pipeline works, where it fails and why publishers sue.
ppc.land
September 20, 2026 at 8:25 AM
Explaining retrieval-augmented generation #AI #MachineLearning #NaturalLanguageProcessing #RAG #InformationRetrieval
Explaining retrieval-augmented generation #AI #MachineLearning #NaturalLanguageProcessing #RAG #InformationRetrieval
Explaining retrieval-augmented generation
Retrieval-augmented generation (RAG) makes a language model fetch documents before it answers. How the pipeline works, where it fails and why publishers sue.
ppc.land
September 20, 2026 at 8:25 AM
Explaining retrieval-augmented generation #AI #MachineLearning #NaturalLanguageProcessing #RAG #InformationRetrieval
Leaving SEASON after 3 days of discussing the current state of search engines and their effects on society.
3 months until the DESIRES abstract deadline. Time to think about where search might go next 🚀🚀🚀
desires-conf.org/2027
#DESIRES2027 #InformationRetrieval #Search #GenerativeAI #AgenticAI
3 months until the DESIRES abstract deadline. Time to think about where search might go next 🚀🚀🚀
desires-conf.org/2027
#DESIRES2027 #InformationRetrieval #Search #GenerativeAI #AgenticAI
DESIRES 2027 – Cologne, Germany
The conference for discussing visionary ideas in search and retrieval systems
desires-conf.org
September 18, 2026 at 4:05 PM
Leaving SEASON after 3 days of discussing the current state of search engines and their effects on society.
3 months until the DESIRES abstract deadline. Time to think about where search might go next 🚀🚀🚀
desires-conf.org/2027
#DESIRES2027 #InformationRetrieval #Search #GenerativeAI #AgenticAI
3 months until the DESIRES abstract deadline. Time to think about where search might go next 🚀🚀🚀
desires-conf.org/2027
#DESIRES2027 #InformationRetrieval #Search #GenerativeAI #AgenticAI
There’s more to a search query than keywords vs. natural language.
A practical taxonomy of 9 dimensions for thinking about search queries, and what they mean for search systems.
#InformationRetrieval #SearchTech
www.searchplex.net/blog/types-o...
A practical taxonomy of 9 dimensions for thinking about search queries, and what they mean for search systems.
#InformationRetrieval #SearchTech
www.searchplex.net/blog/types-o...
Types of Search Queries: A Practical Map
A query has several characteristics. Which ones matter depends on the engineering decision.
www.searchplex.net
September 16, 2026 at 7:59 AM
There’s more to a search query than keywords vs. natural language.
A practical taxonomy of 9 dimensions for thinking about search queries, and what they mean for search systems.
#InformationRetrieval #SearchTech
www.searchplex.net/blog/types-o...
A practical taxonomy of 9 dimensions for thinking about search queries, and what they mean for search systems.
#InformationRetrieval #SearchTech
www.searchplex.net/blog/types-o...
Congratulations, Dr. Chen, on this achievement, and all the best for this exciting next chapter! 🎓
Follow Catherine's work here:
🔗 Personal Website: catherineschen.github.io
🔗 Google Scholar: scholar.google.com/citations?us...
#FeatureFriday #PhDJourney #InformationRetrieval #ExplainableAI
Follow Catherine's work here:
🔗 Personal Website: catherineschen.github.io
🔗 Google Scholar: scholar.google.com/citations?us...
#FeatureFriday #PhDJourney #InformationRetrieval #ExplainableAI
Homepage - Catherine Chen
I am a researcher who recently defended my PhD at Brown University, where I worked with Carsten Eickhoff in the Health NLP Lab. Stay tuned for where I'm headed next!
catherineschen.github.io
August 28, 2026 at 12:00 PM
Congratulations, Dr. Chen, on this achievement, and all the best for this exciting next chapter! 🎓
Follow Catherine's work here:
🔗 Personal Website: catherineschen.github.io
🔗 Google Scholar: scholar.google.com/citations?us...
#FeatureFriday #PhDJourney #InformationRetrieval #ExplainableAI
Follow Catherine's work here:
🔗 Personal Website: catherineschen.github.io
🔗 Google Scholar: scholar.google.com/citations?us...
#FeatureFriday #PhDJourney #InformationRetrieval #ExplainableAI
And this one too!
An Eye Tracking Study: Are AI Overviews Changing Search Behavior?
https://www.johannetrippas.com/papers/allawati2026eye.pdf #sigir26 #ai #search #informationretrieval
An Eye Tracking Study: Are AI Overviews Changing Search Behavior?
https://www.johannetrippas.com/papers/allawati2026eye.pdf #sigir26 #ai #search #informationretrieval
July 21, 2026 at 8:18 PM
And this one too!
An Eye Tracking Study: Are AI Overviews Changing Search Behavior?
https://www.johannetrippas.com/papers/allawati2026eye.pdf #sigir26 #ai #search #informationretrieval
An Eye Tracking Study: Are AI Overviews Changing Search Behavior?
https://www.johannetrippas.com/papers/allawati2026eye.pdf #sigir26 #ai #search #informationretrieval
My little OMINO UK tour is coming to an end. It was a great opportunity to discuss our work on information overload and academic information access with friends, project partners and former colleagues!
#InformationOverload #FakeScience #InformationRetrieval
#InformationOverload #FakeScience #InformationRetrieval
February 20, 2026 at 9:44 AM
My little OMINO UK tour is coming to an end. It was a great opportunity to discuss our work on information overload and academic information access with friends, project partners and former colleagues!
#InformationOverload #FakeScience #InformationRetrieval
#InformationOverload #FakeScience #InformationRetrieval
One week to go until our ELLIS ESSIR Summer School on Information Retrieval starts in Wolverhampton, UK. We are excited! Still possible to register and join the other talented and leading researchers!
👉 2025.essir.eu
#InformationRetrieval #AI #ArtificialIntelligence #LLM #IR #NLP #HCI
👉 2025.essir.eu
#InformationRetrieval #AI #ArtificialIntelligence #LLM #IR #NLP #HCI
ELLIS ESSIR 2025
SCAM ALERT! We have been informed that a company operating under the name Exploreera (using the email address reservation.nl@exploreera.info) is contacting attendees of ESSIR 2025, claiming to offer a...
2025.essir.eu
July 1, 2025 at 3:24 PM
One week to go until our ELLIS ESSIR Summer School on Information Retrieval starts in Wolverhampton, UK. We are excited! Still possible to register and join the other talented and leading researchers!
👉 2025.essir.eu
#InformationRetrieval #AI #ArtificialIntelligence #LLM #IR #NLP #HCI
👉 2025.essir.eu
#InformationRetrieval #AI #ArtificialIntelligence #LLM #IR #NLP #HCI
Registration for ELLIS ESSIR 2025 is open now!
👉 2025.essir.eu/attending/re...
More good news 🎉:
@elsa-ai.bsky.social, the European Lighthouse on Secure and Safe AI, is kindly offering travel support
👉 2025.essir.eu/attending/tr...
#IR #AI #InformationRetrieval #SummerSchool
👉 2025.essir.eu/attending/re...
More good news 🎉:
@elsa-ai.bsky.social, the European Lighthouse on Secure and Safe AI, is kindly offering travel support
👉 2025.essir.eu/attending/tr...
#IR #AI #InformationRetrieval #SummerSchool
May 9, 2025 at 4:33 PM
Registration for ELLIS ESSIR 2025 is open now!
👉 2025.essir.eu/attending/re...
More good news 🎉:
@elsa-ai.bsky.social, the European Lighthouse on Secure and Safe AI, is kindly offering travel support
👉 2025.essir.eu/attending/tr...
#IR #AI #InformationRetrieval #SummerSchool
👉 2025.essir.eu/attending/re...
More good news 🎉:
@elsa-ai.bsky.social, the European Lighthouse on Secure and Safe AI, is kindly offering travel support
👉 2025.essir.eu/attending/tr...
#IR #AI #InformationRetrieval #SummerSchool
SCOLIA 2025, the 1st Intl. Workshop on Scholarly Information Access, succeeds our BIR series. Join us at ECIR 2025 in Lucca to explore IR, NLP, and Scientometrics. CfP below!
sites.google.com/view/bir-ws/...
#informationretrieval #scientometrics #ai #nlp
@suzanv.bsky.social @gcabanac.cpesr.fr
sites.google.com/view/bir-ws/...
#informationretrieval #scientometrics #ai #nlp
@suzanv.bsky.social @gcabanac.cpesr.fr
SCOLIA (BIR) - SCOLIA 2025
SCOLIA 2025
First International Workshop on Scholarly Information Access
sites.google.com
November 30, 2024 at 11:47 AM
SCOLIA 2025, the 1st Intl. Workshop on Scholarly Information Access, succeeds our BIR series. Join us at ECIR 2025 in Lucca to explore IR, NLP, and Scientometrics. CfP below!
sites.google.com/view/bir-ws/...
#informationretrieval #scientometrics #ai #nlp
@suzanv.bsky.social @gcabanac.cpesr.fr
sites.google.com/view/bir-ws/...
#informationretrieval #scientometrics #ai #nlp
@suzanv.bsky.social @gcabanac.cpesr.fr
We’re hiring a Reader (Associate Professor equivalent) in AI at the University of Wolverhampton. More info at jobs.wlv.ac.uk/vacancy/read...
#JobAlert #job #AI #InformationRetrieval #NLP #ComputerVision
#JobAlert #job #AI #InformationRetrieval #NLP #ComputerVision
November 28, 2023 at 6:20 PM
We’re hiring a Reader (Associate Professor equivalent) in AI at the University of Wolverhampton. More info at jobs.wlv.ac.uk/vacancy/read...
#JobAlert #job #AI #InformationRetrieval #NLP #ComputerVision
#JobAlert #job #AI #InformationRetrieval #NLP #ComputerVision