Large Language Models (LLMs) are prone to generating factually incorrect information when responding to queries that involve numerical and statistical data or other timely facts. In this paper, we present an approach for enhancing the accuracy of LLMs by integrating them with Data Commons, a vast, open-source repository of public statistics from trusted organizations like the United Nations (UN), Center for Disease Control and Prevention (CDC) and global census bureaus. We explore two primary methods: Retrieval Interleaved Generation (RIG), where the LLM is trained to produce natural language queries to retrieve data from Data Commons, and Retrieval Augmented Generation (RAG), where relevant data tables are fetched from Data Commons and used to augment the LLM's prompt. We evaluate these methods on a diverse set of queries, demonstrating their effectiveness in improving the factual accuracy of LLM outputs. Our work represents an early step towards building more trustworthy and reliable LLMs that are grounded in verifiable statistical data and capable of complex factual reasoning.

The most vulnerable silo in the world isn't a forgotten storage drive or an isolated repository. When the flow of information is severed between people, body or byte, they wither away. Who, then, is more siloed in communities than a person without a home? Homelessness is a crisis of isolation and a crisis of information access. Homeless people often have a multitude of needs that span across government services and programs.

Apple, on the verge of being the first $1 trillion market capitalization company, constantly looks to expand its business and product and service lines. SAN FRANCISCO -- Could the iCar be hitting the road soon? After CEO Tim Cook admitted last summer that Apple was indeed working on self-driving car technology, the company largely has remained mum on details. But with state permits to operate 55 autonomous cars in California, it seems the iPhone maker could be ready to try out some of its autonomous car tech on Golden State roads. In the latest tally of permits issued as of May 10 for both self-driving cars and drivers approved to monitor such vehicles, the California Department of Motor Vehicles says Apple ranks second only to General Motors' Cruise Automotive, which has permits for 104 vehicles.