Ramanathan V. Guha

Ramanathan V. Guha, Prashanth Radhakrishnan, Bo Xu et al.

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.

Prashanth Radhakrishnan, Jennifer Chen, Bo Xu et al.

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.

Ramanathan V. Guha

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.

Ramanathan V Guha, Vineet Gupta

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.

Ramanathan Guha

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.

R. V. Guha

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.