#InformationRetrieval

2026-02-03

🚨 Early Bird Registration Ends Today! 🚨 The ECIR Conference early bird registration deadline is TODAY. If you’ve been planning to attend, this is your chance to secure your spot at the best rate. 👉 If you’re planning to attend, don’t forget to register. lnkd.in/ejrnYwDw #ECIR #InformationRetrieval

LinkedIn

Carolina Code Conferencecarolinacodes
2026-01-31

ICYMI: AI-Powered Search: Explained in Simple Terms : What is AI-powered search? It's where artificial intelligence meets information retrieval. AI allows computers to behave like people, using machine learning and data science to improve search results. It's not just about chatbots; it's about smarter search. youtube.com/shorts/tflRHOGMj6Q

2026-01-26

RAG-системы: что это такое, принципы работы, архитектура и ограничения

Retrieval-Augmented Generation (RAG) всё чаще упоминается в контексте LLM и всё чаще фигурирует в требованиях к разработчикам, но за этим термином обычно скрывается довольно размытое представление о том, как такие системы реально устроены. В этой статье я разбираю RAG как архитектурный подход: зачем он вообще появился, какие задачи решает, как выглядит базовый пайплайн от данных до ответа модели и где на практике чаще всего возникают проблемы.

habr.com/ru/articles/989000/

#rag #llm #retrieval #nlp #embeddings #semanticsearch #informationretrieval

Carolina Code Conferencecarolinacodes
2026-01-20

AI-Powered Search: Explained in Simple Terms : What is AI-powered search? It's where artificial intelligence meets information retrieval. AI allows computers to behave like people, using machine learning and data science to improve search results. It's not just about chatbots; it's about smarter search. youtube.com/shorts/tflRHOGMj6Q

George Macgregorg3om4c@code4lib.social
2026-01-19

A useful exploration of #AI assistants in #search, using the Primo Research Assistant (PRA) as a case study. This is especially relevant to research #libraries because, anecdotally at least, many libraries have disabled the PRA. The results here suggest a more nuanced approach to whether institutions should choose to enable or disable.

AI-Infused Discovery Environments
Information #Retrieval Boon or Overpromised Hype? doi.org/10.5860/ital.v44i4.174 #InformationRetrieval #DigitalLibraries

George Macgregorg3om4c@code4lib.social
2026-01-14

A cool paper with thought provoking perspectives, by an old colleague!

"This paper proposes that information access systems should be seen not just as #retrieval engines but as didactic environments with the potential to #teach, guide, and #scaffold."

[2601.08035] From Tool to Teacher: Rethinking Search Systems as Instructive Interfaces
arxiv.org/abs/2601.08035 #search #HCI #informationretrieval #pedagogy #CHIIR2026

2025-12-29

The PDF of the full #IRRJ issue, Volume 1 Number 2 of December 2025 is now available online at: irrj.org/issue/view/vol1no2 #InformationRetrieval

2025-12-22

In the second issue of #IRRJ, Paul Kantor writes the editorial, arguing for a more critical adoption of generative AI in information retrieval. He puts his concerns under three distinct headings: consistency, confidence, and completeness. #GenAI, #GenerativeAI, #InformationRetrieval

irrj.org/article/view/25004

2025-12-19

By chance I've just discovered my 2021 keynote at the GNDCon 2.0 (not as usual at the German National Library in Frankfurt, but online due to COVID19) entitled "Die Welt ist klein und man trifft sich immer zweimal..." (It's a small world and you always meet twice...)

youtube.com/watch?v=bkj1GxoLT9g

#semanticweb #knowledgegraphs #yovisto #gnd #gndcon @DNB_Aktuelles @dbpedia @wikidata @tibhannover #informationretrieval #videosearch #AI

2025-12-15

Published at #IRRJ: "Emancipatory Information Retrieval" by Bhaskar Mitra. #InformationRetrieval, #Society, #EmancipatoryPraxis, #TechnologyAndPower

doi.org/10.54195/irrj.24531

2025-12-11

🎖️ Call for Nominations – The Keith van Rijsbergen (KvR) Award 2026 Read more about the award, nomination process, and find the form to submit your nominations here: lnkd.in/emecdsXm #ECIR2026 #InformationRetrieval #Awards #ResearchExcellence ecir2026.eu/calls/keith-...

Keith van Rijsbergen Award

2025-12-10

Published at #IRRJ: "Exploring Embedding Interpretability by Correspondences Between Topic Models and Text Embeddings" by Meng Yuan, Lida Rashidi, and Justin Zobel. #InformationRetrieval, #EmbeddingInterpretability, #Explanability, #TopicModelling

doi.org/10.54195/irrj.23703

2025-12-02

Yue’s research interests lie in natural language processing and information retrieval. Her recent work focuses on LLM-powered AI agents, on advancing the factualness, faithfulness, and trustworthiness of large language models, and on developing and analysing multimodal foundation models.

🔗 Yue’s Webpage: fengyue-leah.github.io/

#UKPLab #NLP #InformationRetrieval #LargeLanguageModels #AIResearch #Multimodality #PeerReview #AISafety #TrustworthyAI

2025-12-02

Published at #IRRJ: "An Eigensystem for Topic Term Weighting yields Fair and Effective Document Rankings" by Massimo Melucci. #InformationRetrieval, #GroupFairness, #ProbabilityRankingPrinciple, #Eigensystem

doi.org/10.54195/irrj.23480

"A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges"

Great 62 page overview of the RAG field.
RAG couples a neural retriever with a generative language model, grounding output in up-to-date, non-parametric memory while retaining the semantic generalisation stored in model weights.

Full paper:
arxiv.org/abs/2508.06401

AI summary:
emergentmind.com/papers/2508.0

#research #RAG #AItools #science #medicine #informationRetrieval

"Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG"

Traditional RAG systems conflate two fundamentally distinct retrieval objectives: (1) precise localization of relevant knowledge and (2) assembly of contextually sufficient evidence for downstream reasoning. This paper formalizes and resolves the resulting structural tension by introducing the Search-Is-Not-Retrieve (SINR) framework.

emergentmind.com/papers/2511.0

#research #informationRetrieval #RAG

The Search-Is-Not-Retrieve (SINR) framework formalizes this tension and resolves it through a dual-layer representation. It introduces two distinct data units:

    •

    Search chunks (si∈S): small, semantically dense segments (roughly 100–200 tokens) optimized for matching relevant content.
    •

    Retrieve chunks (rj∈R): larger segments (roughly 600–1000 tokens) that preserve context and support reasoning and comprehension.
2025-11-14

Und wir haben am @IBI_HU am Lehrstuhl #InformationRetrieval (wo ich auch bin) auch eine tolle Stelle ausgeschrieben:

haushalt-und-personal.hu-berli

100% für 2 Jahre als WiMi im Projekt „SoNAR - Social Network Analysis and related Research“.

Am IBI kann man sich sehr zuhause fühlen. Ich sitze lieber im Büro als im Homeoffice und freu mich immer über den Austausch mit den Kolleg*innen und das wertschätzende und hilfsbereite Klima hier.

Bew.frist: 28.11.
#Jobs #JobsInAcademia #HUBerlin #IBI #LIS

2025-10-27

Published at #IRRJ: "Effectiveness of In-Context Learning for Due Diligence: A Reproducibility Study of Identifying Passages for Due Diligence by Madhukar Dwivedi and Jaap Kamps. #InformationRetrieval, #LegalSearch, #DueDiligence, #PassageRetrieval

doi.org/10.54195/irrj.22626

Client Info

Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst