arXiv AI

DRL: A Deterministic Relational Middleware Layer for Transaction-Safe Enterprise NL2SQL Under Schema-Graph Scaling

The paper introduces DRL, a deterministic relational middleware layer designed to enable transaction-safe natural‑language to SQL (NL2SQL) interfaces over large enterprise OLTP catalogs. DRL interposes between front‑ends and SQL back‑ends, employing dynamic context pruning, relational AST typing, and transactional safeguards (EXPLAIN gating and NULL guards) to keep context within LLM attention limits and detect silent divergence. Experiments on PostgreSQL and MySQL show significant context reductions (up to 92%) and high execution match rates (≈53%) for GPT‑4o, Claude Sonnet 4.5, and Gemini 2.5 Flash, while also revealing that evaluation code quality can materially affect reported performance gaps.

arXiv AI
4d ago

ESQ-Bench: A Multi-Tier Enterprise Oracle Benchmark for Evaluating NL2SQL Dialect Generalization and Silent Semantic Divergence

ESQ‑Bench is an Oracle‑first NL2SQL benchmark that introduces systematic complexity tiers and silent‑divergence evaluation across three enterprise schema levels. It provides six populated schemas (465 tables, 164,682 rows) on Oracle, PostgreSQL, MySQL, and SQL Server, along with 550 gold‑validated question‑query pairs and a four‑metric evaluation harness. The benchmark reveals that state‑of‑the‑art models such as GPT‑4o and Claude Sonnet 4.6 experience significant drops in execution accuracy and high silent‑divergence rates as schema complexity increases, highlighting a gap between closed‑API models and open‑weight baselines on enterprise Oracle schemas.

By Sanjay Mishra, Divya Chukkapalli, Ganesh R. Naik
arXiv AI
Jul 28

Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL

arXiv:2607. 22572v1 Announce Type: new Abstract: Large language models can generate fluent SQL from natural language, but on real enterprise Oracle databases they frequently fail at execution time: columns and aliases are hallucinated and dialect-specific syntax is missed, leading to ORA-00904 invalid-identifier errors.

By Sanjay Mishra, Divya Chukkapalli, Ganesh R. Naik
arXiv AI
Jul 21

An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation and Counterfactual Reasoning Evaluation

arXiv:2607. 17269v1 Announce Type: new Abstract: Large language models encode world models implicitly in neural weights, which exposes four structural risks in high-precision domains such as medicine and finance: hallucination, frozen knowledge, poor explainability, and poor modifiability.

By Zhanbo Li, Shifeng Wu, Xiangjin Meng, Wenjie Cai
Hugging Face Trending Papers
Jun 29

How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD

Organizations that cannot send data to a cloud API increasingly ask: how good is Text-to-SQL if the model must run on-premises on open weights, and which popular accuracy "recipes" are worth their compute? We answer with an honest, fully reproducible benchmark on the BIRD development split (n=1534, Execution Accuracy), evaluating three open model families across two generations -- Qwen2.

arXiv AI
2d ago

GROUND: Reducing Hallucinations in LLM-Based Enterprise Analytics Through Governed Semantic Definitions

The paper introduces GROUND, a framework that limits large language model (LLM) analytics to a governed semantic layer for enterprise data warehouses. GROUND supplies approved metrics, dimensions, join paths, filters, and security rules, then validates generated SQL against these constraints before execution, retrying or abstaining on violations. In benchmarks, GROUND eliminates hallucinations across all evaluated categories and prevents row‑level security breaches, outperforming schema‑only, schema‑RAG, and semantic‑only approaches.

By Aravind Sasidharan Pillai
arXiv AI
Jul 22

BatchDAG: LLM-Planned Execution Graphs for Scalable Ad-Hoc Analysis Over Enterprise Data

arXiv:2607. 18241v1 Announce Type: new Abstract: Large language models (LLMs) excel at analyzing individual documents but break down on exhaustive, cross-entity analytical questions over enterprise-scale datasets due to context overflow, loss of per-entity attribution, and linear latency from sequential tool calls.

By Anupreet Walia