Database Normalization via Dual-LLM Self-Refinement
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912558609334272 |
|---|---|
| author | Jo, Eunjae Lee, Nakyung Kim, Gyuyeong |
| author_facet | Jo, Eunjae Lee, Nakyung Kim, Gyuyeong |
| contents | Database normalization is crucial to preserving data integrity. However, it is time-consuming and error-prone, as it is typically performed manually by data engineers. To this end, we present Miffie, a database normalization framework that leverages the capability of large language models. Miffie enables automated data normalization without human effort while preserving high accuracy. The core of Miffie is a dual-model self-refinement architecture that combines the best-performing models for normalized schema generation and verification, respectively. The generation module eliminates anomalies based on the feedback of the verification module until the output schema satisfies the requirement for normalization. We also carefully design task-specific zero-shot prompts to guide the models for achieving both high accuracy and cost efficiency. Experimental results show that Miffie can normalize complex database schemas while maintaining high accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17693 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Database Normalization via Dual-LLM Self-Refinement Jo, Eunjae Lee, Nakyung Kim, Gyuyeong Databases Artificial Intelligence Computation and Language Database normalization is crucial to preserving data integrity. However, it is time-consuming and error-prone, as it is typically performed manually by data engineers. To this end, we present Miffie, a database normalization framework that leverages the capability of large language models. Miffie enables automated data normalization without human effort while preserving high accuracy. The core of Miffie is a dual-model self-refinement architecture that combines the best-performing models for normalized schema generation and verification, respectively. The generation module eliminates anomalies based on the feedback of the verification module until the output schema satisfies the requirement for normalization. We also carefully design task-specific zero-shot prompts to guide the models for achieving both high accuracy and cost efficiency. Experimental results show that Miffie can normalize complex database schemas while maintaining high accuracy. |
| title | Database Normalization via Dual-LLM Self-Refinement |
| topic | Databases Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2508.17693 |