Data Systems for AI

LLM-Enhanced Databases

Language models as efficient database operators

Active Research

Overview

IOLM-DB compiles recurring semantic operators over table columns into specialized models that are 1.8 to 2.8 times smaller in memory than the general-purpose model. Our semantic cache for OLAP canonicalizes SQL and natural-language queries with an LLM and reaches an 82% hit rate with zero false hits.

Related Publications

IOLM-DB (Information Systems 2026)
Semantic Caching for OLAP (DOLAP 2026)
IOLM-DB (DOLAP 2025)