KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration
This addresses the problem of usability and explainability in multimodal database management for users dealing with complex queries and diverse data types, representing a novel integration rather than an incremental improvement.
The authors tackled the difficulty of writing complex SQL and the lack of explainability in multimodal database systems by proposing KathDB, which integrates relational semantics with foundation models and human-AI collaboration to provide explainable answers across data modalities.
Traditional DBMSs execute user- or application-provided SQL queries over relational data with strong semantic guarantees and advanced query optimization, but writing complex SQL is hard and focuses only on structured tables. Contemporary multimodal systems (which operate over relations but also text, images, and even videos) either expose low-level controls that force users to use (and possibly create) machine learning UDFs manually within SQL or offload execution entirely to black-box LLMs, sacrificing usability or explainability. We propose KathDB, a new system that combines relational semantics with the reasoning power of foundation models over multimodal data. Furthermore, KathDB includes human-AI interaction channels during query parsing, execution, and result explanation, such that users can iteratively obtain explainable answers across data modalities.