A new study from the KSE-Web project finds that BM25 retrieval achieves the strongest performance for Khmer semantic search, reaching 0.943 Recall and 0.876 nDCG, outperforming hybrid and dense retrie…
A new study from arXiv (2608.20348v1) characterizes the clinical lost-in-the-middle (CLitM) effect in electronic health record (EHR) processing, where large language models (LLMs) retrieve information…
A developer's guide details nine techniques to improve retrieval quality in Retrieval-Augmented Generation (RAG) systems, including reranking, hybrid search, and context compression. The techniques ad…
A new study finds that lexical BM25 retrieval outperforms sophisticated agentic search methods on large corpora, achieving 50.5 accuracy versus 30.7 for File-System Agent at the largest scale. The gap…
AGY Memory Engine, a zero-dependency SQLite FTS5 fact store and MCP server, delivers sub-2ms local retrieval with 0 MB extra RAM, serving as a persistent semantic backbone for Google Antigravity (agy)…
A production AI tutor's context engineering experiments, detailed in the newsletter LAI #139, found that reducing tokens via summarization increased costs by roughly 2x despite sending 41% fewer token…
GreekBarRetrieval, a new public benchmark for Greek statutory retrieval derived from GreekBarBench, comprises 283 bar-exam questions and 6,308 candidate statutory articles. Testing three BM25 variants…
Researchers introduced Polaris, a system that trains a large language model to generate table descriptions optimized for retrieval effectiveness using Direct Preference Optimization (DPO) on existing …
A new study evaluating retrieval-augmented generation (RAG) systems for Bengali agricultural advisory finds that no single retrieval method is consistently best, with BM25 achieving an R@10 of 0.506 o…
New research highlights advances in AI reliability and efficiency. Σ-Mem and LedgerMind introduce explicit reliability modeling and structured evidence ledgers to reduce hallucinations and enable prov…
NexusMem, a local memory tool for coding agents, records shell commands, git history, and project docs into a SQLite database, serving ranked, token-budgeted slices on demand. The tool, requiring Node…
AletheionAGI, a new grounding enforcement layer for AI agents, claims to block unsupported claims before they reach customers, reporting 93.6% Recall@5 and a 66.5% diagnostic answer score on 979 froze…
A developer built a hybrid retrieval-augmented generation (RAG) support assistant for a fictional B2B SaaS platform, 'Helix,' and found that hybrid search underperformed vector-only retrieval. Control…
A developer has built NexusMem, a local-first memory engine for AI coding agents that indexes git history, shell commands, project docs, and assistant transcripts into a SQLite database, serving ranke…
A developer benchmarked a homelab agent memory stack on the LoCoMo benchmark and improved accuracy from 63% to 80% by adding hybrid search with BM25 and a local reranker. The developer found that dens…
A developer overhauled their hybrid retrieval pipeline for technical documentation, combining Qwen embeddings, BM25 sparse vectors, and reciprocal rank fusion with a FastEmbed reranker. The upgrade im…
A developer's guide to vector search fundamentals for RAG design covers ANN algorithms like HNSW, distance metrics, metadata filtering, and BM25. It explains trade-offs between accuracy, speed, and co…
A developer found that BM25's default length normalization parameter (b=0.75) systematically penalizes long RAG chunks, causing exact-answer chunks to rank below irrelevant headings. The analysis show…
A new tutorial from StarTrail-org introduces PixelRAG, a pixel-native retrieval-augmented generation pipeline that renders web pages and PDFs as images, divides them into overlapping tiles, and genera…
A developer seeking advice on building a retrieval-augmented generation (RAG) system for government and internal organizational documents asks about optimal chunk sizes for BM25 and semantic search (c…