Live intelligence

Latest AI updates

2 updates
Products

Tabular search in Amazon Bedrock Managed Knowledge Base answers analytical questions across tables and documents

Amazon Bedrock Managed Knowledge Base now supports tabular search, enabling agentic retrieval to run code over CSV, XLSX, or XLS files in an isolated sandbox to compute answers across entire tables. This addresses limitations of passage-based RAG for long or wide tables. The post includes a walkthrough with sample finance files, showing how to build a knowledge base, sync data, and query across tables and documents with citations and trace events.

Amazon Bedrock Managed Knowledge Basetabular searchagentic retrieval
Research

Cited but Unused: Parametric Provenance in Retrieval-Augmented Generation

This arXiv paper measures whether citations in retrieval-augmented generation actually reflect retrieved context or instead come from a model's parametric memory. Using counterfactual value substitution, it finds that 1.2% to 15.7% of citable claims across model families derive from parametric memory, with rates rising with model size within a family. Standard natural language inference verification performs no better than chance, even when restricted to the cited passage. Comparing ten attribution methods, the paper finds that the contrast between a model's output distribution with and without context best separates provenance, but the resulting detector remains too inaccurate to act on.

RAGcitation provenanceparametric memory