mlsanityData to 7 Oct 2026

EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routing

arXiv 2503.22402 ↗First posted 28 Mar 2025cs.DB cs.AI cs.CLcited by 13

Not on the map. Why?

Abstract (arXiv)

Text-to-SQL automatically translates natural language queries to SQL, allowing non-technical users to retrieve data from databases without specialized SQL knowledge. Despite the success of advanced LLM-based Text-to-SQL approaches on leaderboards, their unsustainable computational costs--often overlooked--stand as the "elephant in the room" in current leaderboard-driven research, limiting their economic practicability for real-world deployment and widespread adoption. To tackle this, we exploratively propose EllieSQL, a complexity-aware routing framework that assigns queries to suitable SQL generation pipelines based on estimated complexity. We investigate multiple routers to direct simple queries to efficient approaches while reserving computationally intensive methods for complex cases. Drawing from economics, we introduce the Token Elasticity of Performance (TEP) metric, capturing cost-efficiency by quantifying the responsiveness of performance gains relative to token investment in SQL generation. Experiments show that compared to always using the most advanced methods in our study, EllieSQL with the Qwen2.5-0.5B-DPO router reduces token use by over 40% without compromising performance on Bird development set, achieving more than a 2x boost in TEP over non-routing approaches. This not only advances the pursuit of cost-efficient Text-to-SQL but also invites the community to weigh resource efficiency alongside performance, contributing to progress in sustainable Text-to-SQL. Our source code and model are available at https://elliesql.github.io/.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 30 of its 38 references that are in the map. First posted on arXiv 28 Mar 2025.

Builds on

30 of 38 references.

References · 30

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  3. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  4. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  5. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  6. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  7. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  8. 2024AFlow: Automating Agentic Workflow Generationcited by 395
  9. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  10. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 354
  11. 2023Large Language Model Routing with Benchmark Datasetscited by 166
  12. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
18 more
  1. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Taskscited by 150
  2. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 141
  3. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  4. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  5. 2024RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Modelscited by 84
  6. 2024The Dawn of Natural Language to SQL: Are We Fully Ready?cited by 78
  7. 2024Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Datacited by 61
  8. 2025Atom of Thoughts for Markov LLM Test-Time Scalingcited by 54
  9. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 51
  10. 2024ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answeringcited by 50
  11. 2022Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systemscited by 43
  12. 2024BEAVER: An Enterprise Benchmark for Text-to-SQLcited by 37
  13. 2025Self-Supervised Prompt Optimizationcited by 37
  14. 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Searchcited by 33
  15. 2025NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translationcited by 31
  16. 2024Are Large Language Models Good Statisticians?cited by 26
  17. 2024You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQLcited by 11
  18. 2024Towards Optimizing SQL Generation via LLM Routingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 7.

13 papers.

Sort:

By area:

  1. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  2. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
  3. 2025Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewardscited by 25
  4. 2025Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarkingcited by 21
  5. 2025ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLcited by 8
  6. 2025CONCUR: A Framework for Continual Constrained and Unconstrained Routingcited by 1
  7. 2026Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQLcited by 1
  8. 2026BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQLcited by 1
  9. 2026Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQLcited by 1
  10. 2026An Agentic System for Schema Aware NL2SQL Generationcited by 0
  11. 2026ROSE: An Intent-Centered Evaluation Metric for NL2SQLcited by 0
  12. 2026DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQLcited by 0
1 more
  1. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnessescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL
  2. 2026CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
  3. 2025Rethinking Agentic Workflows: Evaluating Inference-Based Test-Time Scaling Strategies in Text2SQL Tasks
  4. 2026Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis
  5. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL
  6. 2025Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning
  7. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL
  8. 2025Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration