Towards Optimizing SQL Generation via LLM Routing

arXiv:2411.04319 · cs.DB, cs.AI, cs.LG · Submitted 2024-11-06 · Read on arXiv

cs.DB, cs.AI, cs.LG

Submitted: 2024-11-06

Updated: 2024-11-06

Comments: Table Representation Learning Workshop at NeurIPS 2024

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 25× in this paper · explained in 1 episode
• Text-to-SQL — 20× in this paper · explained in 3 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Natural Language Interfaces to Databases - An Introduction
• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
• CHESS: Contextual Harnessing for Efficient SQL Synthesis
• Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL
• LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
• The Dawn of Natural Language to SQL: Are We Fully Ready?
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
• A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?
• The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models
• End-to-end Text-to-SQL Generation within an Analytics Insight Engine
• RouteLLM: Learning to Route LLMs with Preference Data
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
• Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
• Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey

Related papers

• Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries
• Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering
• Bridging Business Intent and Data: A Benchmark for Automatic Relational Data Product Generation
• DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation
• MaDI-Bench: An End-to-End Data Integration Benchmark
• Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Mediated Reasoning