AI Glossary
What is RAG (Retrieval-Augmented Generation)?
RAG bolts a search step onto generation: a query is embedded, similar documents are retrieved from a vector database, and those documents are placed in the prompt so the model answers from them instead of memory. It is the standard pattern for grounding models in private or fresh data and reducing hallucination.
News momentum
Mentions in recent AI news titles and summaries, refreshed from the ingestion stream.
31
+5 vs prior 7d
- Graph Topology Meets Energy-Driven Pathfinding: Preserving Contextual Consistency in Retrieval-Augmented Generation
arxiv-ai · 15h
- MAPS: Macro-Adaptive Parallel Reasoning for Regulating Search Momentum in Retrieval-Augmented Generation
arxiv-ai · 17h
- Retrieval Augmented Generation Compositionality
arxiv-ai · 18h
- C$^2$U in RAG: Compositional Concept Unlearning in Retrieval-Augmented Generation
arxiv-ai · 1d