retrieval-augmented generation
PulseAugur coverage of retrieval-augmented generation — every cluster mentioning retrieval-augmented generation across labs, papers, and developer communities, ranked by signal.
- 2026-05-10 research_milestone A study empirically analyzed byte-exact deduplication in RAG systems, demonstrating significant context reduction without quality loss. source
- 2026-05-10 research_milestone A study assessed RAG and fine-tuning for industrial question-answering applications, finding RAG to be more cost-effective. source
3 day(s) with sentiment data
-
Deterministic Legal Agents API enables auditable reasoning over temporal knowledge graphs
Researchers have introduced a new API called SAT-Graph API designed for auditable reasoning over temporal knowledge graphs, particularly in legal contexts. This API aims to overcome the limitations of standard Retrieval…
-
Study evaluates Generative AI virtual assistant for university project support
Researchers have developed a virtual assistant to help students at Maastricht University with project regulations, addressing common LLM issues like hallucinations and inaccurate responses. The system utilizes Retrieval…
-
NeocorRAG framework optimizes retrieval quality for RAG models, achieving SOTA performance
Researchers have introduced NeocorRAG, a novel framework designed to enhance Retrieval-Augmented Generation (RAG) systems by focusing on retrieval quality rather than just recall. This new approach utilizes "Evidence Ch…
-
New RAG system aids navigation of global AI regulations
Researchers have developed a new Retrieval-Augmented Generation (RAG) system designed to help users navigate the complex landscape of global AI regulations. The system processes a corpus of 242 documents from 68 jurisdi…
-
Researchers develop new methods for knowledge graph retrieval and completion
Researchers have developed new frameworks to enhance knowledge graph completion and visual question answering by integrating multimodal knowledge graphs with retrieval-augmented generation techniques. One approach, RADD…
-
OntoLogX uses LLMs to extract actionable threat intelligence from cybersecurity logs
Researchers have developed OntoLogX, an AI agent designed to extract Cyber Threat Intelligence (CTI) from raw cybersecurity logs. The system utilizes Large Language Models (LLMs) combined with a lightweight log ontology…
-
New RAG chunk filtering method slashes vector index size by 36%
A new research paper proposes methods to reduce redundancy in Retrieval-Augmented Generation (RAG) systems. The study focuses on chunk filtering techniques, including semantic, topic-based, and named-entity-based approa…
-
New RAG research tackles tabular data, cost, and cross-lingual knowledge
Several recent research papers explore advancements in Retrieval-Augmented Generation (RAG) systems. One paper introduces Orthogonal Subspace Decomposition (OSD) to separate task-specific behavior from document knowledg…
-
S2G-RAG framework improves multi-hop QA by judging evidence sufficiency
Researchers have introduced S2G-RAG, an iterative framework designed to improve retrieval-augmented question answering, particularly for multi-hop queries. The system features a controller called S2G-Judge that determin…
-
Researchers explore Query Performance Prediction for optimizing RAG pipelines
Researchers have explored using Query Performance Prediction (QPP) to optimize Retrieval-Augmented Generation (RAG) pipelines by selecting the most effective query variant. This approach aims to reduce computational cos…
-
LLM prompts extract software goals with 61% accuracy, aiding manual efforts
Researchers have developed a method using a chain of LLMs with engineered prompts to automate the extraction of functional goals from software documentation. This approach involves actor identification and high/low-leve…
-
ZeroEntropy offers specialized AI models for faster, more accurate RAG pipelines
ZeroEntropy has developed specialized AI models, including rerankers and embeddings, designed for production systems that prioritize speed and accuracy over generalist models. Their offerings, such as zembed-1 and zeran…
-
Hugging Face and Intel collaborate on Gaudi accelerators for efficient AI
Hugging Face has released new resources and guides detailing how to leverage Intel's Gaudi 2 AI accelerators for efficient AI model training and deployment. These collaborations focus on optimizing performance for tasks…
-
Text embeddings in RAG systems may not be as secure as assumed
A recent paper titled "Text Embeddings Reveal As Much as Text" explores the security implications of using text embeddings in Retrieval Augmented Generation (RAG) systems. The research questions whether embedding vector…