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.

Publicly available data from open sources (e.g., United States Census Bureau (Census), World Health Organization (WHO), Intergovernmental Panel on Climate Change (IPCC)) are vital resources for policy makers, students and researchers across different disciplines. Combining data from different sources requires the user to reconcile the differences in schemas, formats, assumptions, and more. This data wrangling is time consuming, tedious and needs to be repeated by every user of the data. Our goal with Data Commons (DC) is to help make public data accessible and useful to those who want to understand this data and use it to solve societal challenges and opportunities. We do the data processing and make the processed data widely available via standard schemas and Cloud APIs. Data Commons is a distributed network of sites that publish data in a common schema and interoperate using the Data Commons APIs. Data from different Data Commons can be joined easily. The aggregate of these Data Commons can be viewed as a single Knowledge Graph. This Knowledge Graph can then be searched over using Natural Language questions utilizing advances in Large Language Models. This paper describes the architecture of Data Commons, some of the major deployments and highlights directions for future work.

As efforts advance around the globe, the US falls behind.

The repurposing of biomedical data is inhibited by its fragmented and multi-formatted nature that requires redundant investment of time and resources by data scientists. This is particularly true for Type 1 Diabetes (T1D), one of the most intensely studied common childhood diseases. Intense investigation of the contribution of pancreatic β-islet and T-lymphocytes in T1D has been made. However, genetic contributions from B-lymphocytes, which are known to play a role in a subset of T1D patients, remain relatively understudied. We have addressed this issue through the creation of Biomedical Data Commons (BMDC), a knowledge graph that integrates data from multiple sources into a single queryable format. This increases the speed of analysis by multiple orders of magnitude. We develop a pipeline using B-lymphocyte multi-dimensional epigenome and connectome data and deploy BMDC to assess genetic variants in the context of Type 1 Diabetes (T1D). Pipeline-identified variants are primarily common, non-coding, poorly conserved, and are of unknown clinical significance. While variants and their chromatin connectivity are cell-type specific, they are associated with well-studied disease genes in T-lymphocytes. Candidates include established variants in the HLA-DQB1 and HLA-DRB1 and IL2RA loci that have previously been demonstrated to protect against T1D in humans and mice providing validation for this method. Others are included in the well-established T1D GRS2 genetic risk scoring method. More intriguingly, other prioritized variants are completely novel and form the basis for future mechanistic and clinical validation studies The BMDC community-based platform can be expanded and repurposed to increase the accessibility, reproducibility, and productivity of biomedical information for diverse applications including the prioritization of cell type-specific disease alleles from complex phenotypes.

Representing domain knowledge is crucial for any task. There has been a wide range of techniques developed to represent this knowledge, from older logic based approaches to the more recent deep learning based techniques (i.e. embeddings). In this paper, we discuss some of these methods, focusing on the representational expressiveness tradeoffs that are often made. In particular, we focus on the the ability of various techniques to encode `partial knowledge' - a key component of successful knowledge systems. We introduce and describe the concepts of `ensembles of embeddings' and `aggregate embeddings' and demonstrate how they allow for partial knowledge.

The Internet of Things (IoT) is creating a major shift from the traditional approaches to operating and maintaining all energy systems. With the proliferation of cheap sensors, power grids are generating vast amounts of data and there is an increasing interest around data-driven decision making, or more broadly, energy analytics. Due to the inherent nature of device and data ownership in the power grids, these analytics efforts have been siloed. Energy analytics developers create databases for monolithic applications that lack the infrastructure to quickly transform data between computational resources and persistent data storage, easy dissemination and validation of results, and support integration. We propose a data architecture that supports broader use of data technologies and systems integration guided by publish and subscribe architecture, and polyglot persistence. We provide use cases to discuss our design choices using the electric power grid as the main application domain. However, we believe that the energy industry as a whole can benefit from the proposed architecture.

We present a user modeling system that serves as the foundation of a personal assistant. The system ingests web search history for signed-in users, and identifies coherent contexts that correspond to tasks, interests, and habits. Unlike past work which focused on either in-session tasks or tasks over a few days, we look at several months of history in order to identify not just short-term tasks, but also long-term interests and habits. The features we use for identifying coherent contexts yield substantially higher precision and recall than past work. We also present an algorithm for identifying contexts that is 8 to 30 times faster than previous algorithms. The user modeling system has been deployed in production. It runs over hundreds of millions of users, and updates the models with a 10-minute latency. The contexts identified by the system serve as the foundation for generating recommendations in Google Now.

Messages often refer to entities such as people, places and events. Correct identification of the intended reference is an essential part of communication. Lack of shared unique names often complicates entity reference. Shared knowledge can be used to construct uniquely identifying descriptive references for entities with ambiguous names. We introduce a mathematical model for `Reference by Description', derive results on the conditions under which, with high probability, programs can construct unambiguous references to most entities in the domain of discourse and provide empirical validation of these results.

RDF Schema er et vokabularium til datamodellering af RDF-data. RDF Schema er en ekstension af det grundlæggende RDF-vokabularium.

Statements about entities occur everywhere, from newspapers and web pages to structured databases. Correlating references to entities across systems that use different identifiers or names for them is a widespread problem. In this paper, we show how shared knowledge between systems can be used to solve this problem. We present "reference by description", a formal model for resolving references. We provide some results on the conditions under which a randomly chosen entity in one system can, with high probability, be mapped to the same entity in a different system.

Distributed representations (such as those based on embeddings) and discrete representations (such as those based on logic) have complementary strengths. We explore one possible approach to combining these two kinds of representations. We present a model theory/semantics for first order logic based on vectors of reals. We describe the model theory, discuss some interesting properties of such a system and present a simple approach to query answering.

• Ensure your Schema. Org annotations represent the primary content on the page-> ensures correct caption data is shown• Ensure your Schema. Org annotations are appropriate and relevant to the content of the page-> improves your chances of being shown• Rich Captions do not support RDFa 1.1 or JSONLD-> stick with RDFa 1.0 or Microdata for now