Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization

• URL: http://arxiv.org/abs/2609.11141v1
• Date: Thu, 10 Sep 2026 06:34:35 GMT
• Title: Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization
• Abstract summary: Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear.<n>We study this issue through database normalization, involving reasoning about functional dependencies, join decompositions, and inter-table constraints.<n>We introduce a Database Normalization Benchmark (DNBENCH), comprising 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF.
• Score: 5.32197677925365
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear when those outputs must satisfy database-level constraints. We study this issue through database normalization, involving reasoning about functional dependencies, lossless join decompositions, and inter-table constraints. We introduce a Database Normalization Benchmark (DNBENCH), comprising 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF. DNBENCH uses a three-axis protocol to measure semantic equivalence, structural accuracy, and logical validity. Across Single, Complex, and Real World levels, DNBENCH uncovers recurring failures in dependency inference, schema decomposition, and inter-table constraint reconstruction. We further propose Multi-Agent Reasoning for Schemas (MARS), which separates evidence extraction, violation diagnosis, and decomposition planning from schema generation and verification. MARS improves the DNB-SCORE by 82.0% over the single-prompt baseline. All artifacts will be released upon acceptance.

Related papers

• Towards Anomaly Detection on Relational Data [51.473064583839296]
  We propose a reconstruction-based framework that captures anomalies from both attribute and relational edge reconstruction.<n>RelAD consistently outperforms other baselines while achieving competitive efficiency.
  arXiv  Detail & Related papers  (2026-06-17T02:36:32Z)
• Logic-Regularized Verifier Elicits Reasoning from LLMs [63.65875399266337]
  We propose LOVER, an unsupervised verifier regularized by logical rules.<n>Lover treats theverifier as a binary latent variable, utilizinginternal activations and enforcing three logical constraints.<n>Lover significantly outperforms unsupervised baselines.
  arXiv  Detail & Related papers  (2026-05-07T09:03:49Z)
• ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering [55.55968342644846]
  Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering.<n>Existing serialization methods fail to capture explicit hierarchies and lack schema flexibility.<n>We propose ASTRA (Adaptive Semantic Tree Reasoning Architecture) including two main modules, AdaSTR and DuTR.<n> Experiments on complex table benchmarks demonstrate that our method achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-04-10T06:09:41Z)
• DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering [11.177470565638666]
  Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents.<n>Existing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks suffer from critical limitations.<n>We propose DocSage, an end-to-end agentic framework that integrates dynamic schema discovery, structured information extraction, and schema-aware relational reasoning with error guarantees.
  arXiv  Detail & Related papers  (2026-03-12T11:00:09Z)
• PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models [51.42043158297229]
  We introduce Pluel, a framework to synthesize multi-tabular relational databases from scratch.<n>In a step-by-step fashion, Pluel models (1) schemas with directed graphs, (2) inter-table primary-foreign key connectivity with bipartite graphs, and, (3) feature distributions in tables via conditional causal mechanisms.
  arXiv  Detail & Related papers  (2026-02-03T21:35:18Z)
• Routing End User Queries to Enterprise Databases [13.367384894681651]
  We construct realistic benchmarks by extending existing NL-to- datasets.<n>Our study shows that routing becomes increasingly challenging with larger, domain-overlapping DB repositories and ambiguous queries.
  arXiv  Detail & Related papers  (2026-01-27T17:30:19Z)
• DBAIOps: A Reasoning LLM-Enhanced Database Operation and Maintenance System using Knowledge Graphs [25.16965474653075]
  Existing automatic database O&M methods, including commercial products, cannot effectively utilize expert experience.<n>We present DBAIOps, a novel hybrid database O&M system that combines reasonings with knowledge graphs to achieve DBA-style diagnosis.
  arXiv  Detail & Related papers  (2025-08-02T01:36:57Z)
• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [80.88654868264645]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• Retrieval-Augmented Generation of Ontologies from Relational Databases [13.160850863758]
  We present RIGOR, Retrieval-augmented Iterative Generation of RDB Ontologies.<n>An approach that turns relationals into rich schemas with minimal human effort is presented.
  arXiv  Detail & Related papers  (2025-06-02T01:10:05Z)
• Text2Schema: Filling the Gap in Designing Database Table Structures based on Natural Language [22.15408079332362]
  People without a database background usually rely on file systems or tools such as Excel data management.<n> Database systems possess strong management capabilities, but require a high level of professional expertise from users.
  arXiv  Detail & Related papers  (2025-03-31T09:39:19Z)
• ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models [46.07900122810749]
  Large language models (LLMs) have achieved unprecedented performances in various applications, yet evaluating them is still challenging. We contend that utilizing existing relational databases is a promising approach for constructing benchmarks. We propose ERBench, which uses these integrity constraints to convert any database into an LLM benchmark.
  arXiv  Detail & Related papers  (2024-03-08T12:42:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.