MaaSDB: Spatial Databases in the Era of Large Language Models (Vision Paper)
arXiv:2309.17072 · doi:10.1145/3589132.3625597
Abstract
Large language models (LLMs) are advancing rapidly. Such models have demonstrated strong capabilities in learning from large-scale (unstructured) text data and answering user queries. Users do not need to be experts in structured query languages to interact with systems built upon such models. This provides great opportunities to reduce the barrier of information retrieval for the general public. By introducing LLMs into spatial data management, we envisage an LLM-based spatial database system to learn from both structured and unstructured spatial data. Such a system will offer seamless access to spatial knowledge for the users, thus benefiting individuals, business, and government policy makers alike.
arXiv commentAccepted to appear in ACM SIGSPATIAL 2023
References in corpus (7)
- Data Synthesis based on Generative Adversarial Networks
- Faith and Fate: Limits of Transformers on Compositionality
- Multimodal Neural Databases
- Querying Large Language Models with SQL
- Unstructured and structured data: Can we have the best of both worlds with large language models?
- Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables
- DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models