RE: https://researchbuzz.masto.host/@mottg/116474491390856287

Nice, the state of Information Retrieval in 2026 by Mohan Krishna. Lots of interesting references and thoughts, if you're into leaderboards and state-of-the-art performance on benchmark test collections. #InformationRetrieval

"The State of Information Retrieval in 2026"

This is the best survey article I have seen in a long time in this niche.

The dominant retriever in 2026 is an 8-billion-parameter decoder-only language model fine-tuned on synthetic data, conditioned on natural-language instructions, often executing chain-of-thought reasoning before deciding what to retrieve.

https://medium.com/@mohankrishnagr08/the-state-of-information-retrieval-in-2026-192f125a5269

#research #informationRetrieval #RAG #LLM #SPLADE #AIbenchmark #AI

Published at #IRRJ: "Simple Techniques for Efficient Top-k Batch Query Processing" by Zhixuan Li and Joel Mackenzie. #BatchProcessing, #Caching, #DynamicPruning, #EfficientRetrieval, #InformationRetrieval

https://doi.org/10.54195/irrj.23893

Simple Techniques for Efficient Top- k Batch Query Processing | Information Retrieval Research

Looking back at #ECIR2026: Jaap Kamps presented the #IRRJ paper "Effectiveness of In-Context Learning for Due Diligence": https://doi.org/10.54195/irrj.22626 #InformationRetrieval

PageIndex๋Š” ๋ฒกํ„ฐ DB์™€ ์ธ์œ„์  ์ฒญํ‚น์„ ๋ฐฐ์ œํ•˜๊ณ  ๋ฌธ์„œ๋ฅผ ๊ณ„์ธต์  '๋ชฉ์ฐจ(tree)'๋กœ ์ธ๋ฑ์‹ฑํ•ด LLM์œผ๋กœ ์ถ”๋ก  ๊ธฐ๋ฐ˜ ํƒ์ƒ‰์„ ์ˆ˜ํ–‰ํ•˜๋Š” ๋ฒกํ„ฐ๋ฆฌ์Šค RAG ํ”„๋ ˆ์ž„์›Œํฌ์ž…๋‹ˆ๋‹ค. ์ธ๊ฐ„ ์ „๋ฌธ๊ฐ€์ฒ˜๋Ÿผ ๋‹ค๋‹จ๊ณ„ ์ถ”๋ก ์œผ๋กœ ์ •ํ™•ํ•œ ๊ด€๋ จ ๊ตฌ๊ฐ„์„ ์ฐพ์•„ FinanceBench์—์„œ Mafin 2.5๋กœ 98.7% ๋‹ฌ์„ฑ. ์˜คํ”ˆ์†Œ์ŠคยทAPIยท์…€ํ”„ํ˜ธ์ŠคํŠธ ์ œ๊ณต, LiteLLMยทOpenAI Agents SDK ์—ฐ๋™.

https://github.com/VectifyAI/PageIndex

#pageindex #rag #vectorless #reasoning #informationretrieval

GitHub - VectifyAI/PageIndex: ๐Ÿ“‘ PageIndex: Document Index for Vectorless, Reasoning-based RAG

๐Ÿ“‘ PageIndex: Document Index for Vectorless, Reasoning-based RAG - VectifyAI/PageIndex

GitHub

Akshay (@akshay_pachaar)

AI ์—”์ง€๋‹ˆ์–ด๋ฅผ ์œ„ํ•œ 8๊ฐ€์ง€ RAG ์•„ํ‚คํ…์ฒ˜๋ฅผ ์†Œ๊ฐœํ•˜๋ฉฐ, Naive RAG๋ถ€ํ„ฐ ๋‹ค์–‘ํ•œ ๊ฒ€์ƒ‰ยท์ƒ์„ฑ ์กฐํ•ฉ ํŒจํ„ด๊นŒ์ง€ ์šฉ๋„๋ณ„๋กœ ์„ค๋ช…ํ•œ๋‹ค. RAG ์‹œ์Šคํ…œ ์„ค๊ณ„์™€ ๊ตฌํ˜„์„ ๊ณ ๋ฏผํ•˜๋Š” ๊ฐœ๋ฐœ์ž์—๊ฒŒ ์‹ค์šฉ์ ์ธ ์ฐธ๊ณ  ์ž๋ฃŒ๋‹ค.

https://x.com/akshay_pachaar/status/2040050430890405931

#rag #llm #aiengineering #informationretrieval

Akshay ๐Ÿš€ (@akshay_pachaar) on X

8 RAG architectures for AI Engineers: (explained with usage) 1) Naive RAG - Retrieves documents purely based on vector similarity between the query embedding and stored embeddings. - Works best for simple, fact-based queries where direct semantic matching suffices. 2)

X (formerly Twitter)
A practical look at how search indexing is evolving to hybrid retrieval systems that support semantic search, vector search, and AI-driven query understanding. https://hackernoon.com/from-inverted-indexes-to-hybrid-retrieval-rethinking-search-architecture #informationretrieval
From Inverted Indexes to Hybrid Retrieval: Rethinking Search Architecture | HackerNoon

A practical look at how search indexing is evolving to hybrid retrieval systems that support semantic search, vector search, and AI-driven query understanding.

Well i finally did it. I just released my test dataset for AI Evaluation. Its a simulated company, represented by 60,000 documents, the readme in the image explains it all ... If you are interested, its at https://codeberg.org/Lorenz_Systems/Company_Sim.git

#EUAIAct #DigitalSovereignty #SovereignCloud #FOSS #FLOSS #Codeberg #Forgejo #OpenSource #DataGovernance #Auditability #ForensicAI #EUTech #PrivacyByDesign #InformationRetrieval #KnowledgeManagement #DeterministicAI #EUPL

@marlinz #Informationretrieval is depending on the current task and situation.

Sometimes #navigation is the most efficient one, sometimes it's #search. (my #TagTrees are a combination of both) And then there is teleporting, bookmarks/favorites, ...

Unfortunately, most people don't have the knowledge and experience to use multiple methods and decide which method to choose in a specific situation. ๐Ÿ˜ž

#PIM

๐Ÿ‘ฅ Justus-Jonas Erker (UKP Lab/Technische Universitรคt Darmstadt), Nils Reimers (Cohere), Iryna Gurevych (UKP Lab/Technische Universitรคt Darmstadt)

See you at Hashtag#EACL2026 in Rabat ๐Ÿ•Œ!

#UKPLab #NLP #NLProc #InformationRetrieval #DenseRetrieval #MultiHop #FactChecking #QuestionAnswering #RAG