RAG & AI News - Latest artificial intelligence updates
Stay informed about the latest advances in RAG, LLM, and artificial intelligence. Analysis, announcements, and industry trends.
Latest RAG & AI news
BEIR Benchmark 2.0 Leaderboard 2025: Complete NDCG@10 Scores & Rankings
Complete BEIR 2.0 leaderboard with NDCG@10 scores for all top models. Compare Voyage, Cohere, BGE, OpenAI embeddings on the latest benchmark.
New Research: Cross-Encoder Reranking Improves RAG Accuracy by 40%
MIT study demonstrates that two-stage retrieval with cross-encoder reranking significantly outperforms single-stage vector search across multiple benchmarks.
CLaRa: A New Approach to RAG with Continuous Latent Reasoning
CLaRa introduces continuous latent reasoning to bridge retrieval and generation, achieving state-of-the-art performance on QA benchmarks
Claude Opus 4.5 Transforms RAG Performance with Enhanced Context Understanding
Anthropic's latest model delivers breakthrough improvements in retrieval-augmented generation, with superior context handling and reduced hallucinations for enterprise RAG applications.
Microsoft Research Introduces GraphRAG: Combining Knowledge Graphs with RAG
Microsoft Research unveils GraphRAG, a novel approach that combines RAG with knowledge graphs to improve contextual understanding
Advanced Chunking Strategies for RAG Systems in 2025
Recent research reveals new document chunking approaches that significantly improve RAG system performance
Query Decomposition Breakthrough: DecomposeRAG Handles Complex Questions 50% Better
UC Berkeley researchers introduce DecomposeRAG, an automated query decomposition framework that significantly improves multi-hop question answering.
Claude 3.5 Sonnet Optimized for RAG: 500K Context Window and Extended Thinking
Anthropic releases Claude 3.5 Sonnet with extended context window, improved citation accuracy, and new RAG-specific features for enterprise applications.
GPT-4.5 Turbo: OpenAI's New RAG-Optimized Model (Full Specs & Pricing)
GPT-4.5 Turbo specs: 128K context, 50% cheaper than GPT-4, native retrieval, structured output. Complete API guide and migration tips.
Cohere Launches Embed v4: 30% Better Accuracy with Smaller Model Size
Cohere's new embedding model delivers state-of-the-art performance on MTEB benchmark while reducing dimensions from 1024 to 768, cutting costs and improving speed.
Automatic RAG Evaluation: New Framework Achieves 95% Correlation with Human Judgments
Google Research introduces AutoRAGEval, an automated evaluation framework that reliably assesses RAG quality without human annotation.
Weaviate Launches Hybrid Search 2.0 with 60% Faster Query Performance
Weaviate's new hybrid search engine combines BM25, vector search, and learned ranking in a single optimized index for superior RAG retrieval.
Breakthrough in Multimodal RAG: New Framework Handles Text, Images, and Tables
Stanford and DeepMind researchers present MM-RAG, a unified framework for retrieving and reasoning over multiple modalities with 65% accuracy improvement.
Microsoft Releases GraphRAG 2.0 with Enhanced Knowledge Graph Integration
Microsoft Research unveils GraphRAG 2.0, featuring improved entity extraction, relationship mapping, and 40% better accuracy on complex multi-hop queries.
Topics we cover
- New language models (GPT, Claude, Mistral, Llama)
- Advances in RAG and semantic search
- Vector databases (Qdrant, Pinecone, Weaviate)
- Embedding and optimization techniques
- Enterprise use cases
- Ailog updates and new features