iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
Commercial LPG Prices Cut by Over Rs 200; Delhi, Kolkata 19-kg Cylinder Rates Published US Stock Markets Rally as Chip Stock Gains Lift Nasdaq, S&P 500 and Dow SEBI Clarifies Unlisted Share Sale Rules: 200-Buyer Private Deal Limit GeM completes 10 years as India's trusted digital public procurement platform Moody's Assigns First-Time Baa2 Rating to RBL Bank, One Notch Above India's Sovereign Sebi Bars Zee's Subhash Chandra, Punit Goenka From Market for One Year Zepto Defers IPO by Two to Three Quarters After Tepid Investor Response Tim Cook: India Among Apple's Best Global Markets as June Quarter Records Revenue Domestic funds reach record 21% stake in Indian companies as FPI ownership drops to 17% Cybercriminals widen net as assessees rush to meet I-T return filing deadline Commercial LPG Prices Cut by Over Rs 200; Delhi, Kolkata 19-kg Cylinder Rates Published US Stock Markets Rally as Chip Stock Gains Lift Nasdaq, S&P 500 and Dow SEBI Clarifies Unlisted Share Sale Rules: 200-Buyer Private Deal Limit GeM completes 10 years as India's trusted digital public procurement platform Moody's Assigns First-Time Baa2 Rating to RBL Bank, One Notch Above India's Sovereign Sebi Bars Zee's Subhash Chandra, Punit Goenka From Market for One Year Zepto Defers IPO by Two to Three Quarters After Tepid Investor Response Tim Cook: India Among Apple's Best Global Markets as June Quarter Records Revenue Domestic funds reach record 21% stake in Indian companies as FPI ownership drops to 17% Cybercriminals widen net as assessees rush to meet I-T return filing deadline
Home ›› Topics ›› retrieval augmented generation

Topic

retrieval augmented generation

5 stories
New Unifying Lens for Learning to Hash Could Cut Memory Costs in Large-Scale Retrieval Technology
Artificial Intelligence #learning to hash#random projections

New Unifying Lens for Learning to Hash Could Cut Memory Costs in Large-Scale Retrieval

A new arXiv paper from researcher Sean Moran proposes a unifying lens for approximate nearest-neighbour search, framing all methods as variations of projection, quantisation, and organisation. The work introduces the open BitBudget benchmark and finds that quantisation delivers the largest memory savings, with one-bit codes matching uncompressed quality for most embedders at 1/32 the size. The study also shows supervised eight-byte codes can more than double retrieval quality over two-kilobyte floats.

Jun 16, 2026 1 source
RoTRAG Framework Boosts Harm Detection Accuracy by 40% Using Retrieval-Augmented Generation Technology
Artificial Intelligence #rotrag#rule of thumb reasoning

RoTRAG Framework Boosts Harm Detection Accuracy by 40% Using Retrieval-Augmented Generation

Researchers propose RoTRAG, a retrieval-augmented framework that incorporates human-written moral norms (Rules of Thumb) into LLM-based conversation harm detection. The method achieves an average relative F1 gain of around 40% across benchmark datasets and an 8.4% reduction in distributional error.

Jun 16, 2026 1 source
Primacy Bias in Multimodal RAG: First Retrieved Items Dominate, Study Finds Technology
Artificial Intelligence #artificial intelligence#multimodal

Primacy Bias in Multimodal RAG: First Retrieved Items Dominate, Study Finds

A research paper titled 'Lost at the End: Primacy Bias in Multimodal Retrieval-Augmented Question Answering' introduces a controlled probe to measure position bias in multimodal KB-VQA. The study finds a strong primacy effect, where the first retrieved passage significantly outperforms later ones, contrasting with the U-shaped 'lost-in-the-middle' pattern in text-only models. The findings call for reader-side interventions and question the adequacy of recall@k as a metric for deployed systems.

Jun 16, 2026 1 source
RAG and LLMs Combined to Generate Personalized Reading Content at Desired Complexity Technology
Artificial Intelligence #retrieval-augmented generation#llms

RAG and LLMs Combined to Generate Personalized Reading Content at Desired Complexity

A research paper proposes a four-module system that uses Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs) to generate reading content tailored to user queries and complexity preferences. Experiments with Meta LLaMA 4 Scout, LLaMA 3.1 8B Instant, and Google Gemma2 9B show that RAG improves relevance and groundedness by 26–35 percentage points across all models and prompting strategies.

Jun 16, 2026 1 source
CONCORD: Asynchronous Sparse Aggregation Boosts Device-Cloud RAG Efficiency Under Document Isolation Technology
Artificial Intelligence #concord#asynchronous sparse aggregation

CONCORD: Asynchronous Sparse Aggregation Boosts Device-Cloud RAG Efficiency Under Document Isolation

A new framework called CONCORD addresses the challenge of document isolation in device-cloud retrieval-augmented generation (RAG). By treating the cloud as an asynchronous evidence source and introducing waiting debt control and certificate-guided minimal supplementation, CONCORD improves end-to-end throughput by 1.66× to 2.15× over baselines while cutting per-token communication by over two orders of magnitude. Experiments on Natural Questions and WikiText-2 demonstrate comparable answer quality and perplexity.

Jun 16, 2026 1 source