KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909957529534464 |
|---|---|
| author | Xiao, Guorui Zhang, Enhao Sullivan, Nicole Hansen, Will Balazinska, Magdalena |
| author_facet | Xiao, Guorui Zhang, Enhao Sullivan, Nicole Hansen, Will Balazinska, Magdalena |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11067 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration Xiao, Guorui Zhang, Enhao Sullivan, Nicole Hansen, Will Balazinska, Magdalena Databases Artificial Intelligence 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. |
| title | KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration |
| topic | Databases Artificial Intelligence |
| url | https://arxiv.org/abs/2512.11067 |