2 papers
cs.IR2026
SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction
Sin Yu Bonnie Ho, Arlie Coles, Erik Larsson +3
Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when target schemas are large and complex. In such cases, including the ful…
cs.CL2024
Synthetic SQL Column Descriptions and Their Impact on Text-to-SQL Performance
Niklas Wretblad, Oskar Holmström, Erik Larsson +7
Relational databases often suffer from uninformative descriptors of table contents, such as ambiguous columns and hard-to-interpret values, impacting both human users and text-to-S…