A new evaluation framework generates equivalent schemas from an E/R model and shows that LLMs produce SQL queries with different answers across those schemas for fixed questions and data.
hub
The death of schema linking? text-to-sql in the age of well-reasoned language models
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
CA-SQL achieves 51.72% execution accuracy on the challenging tier of the BIRD benchmark using GPT-4o-mini by scaling exploration breadth according to estimated task difficulty, evolutionary prompt seeding, and candidate voting.
EXPO-SQL improves Text-to-SQL by using clause-level rewards derived from execution error messages and incremental clause execution instead of uniform query-level rewards.
EvoMQL uses iterative Draft-Refine-Optimize cycles with execution feedback to reach 76.6% accuracy on EAI and 83.1% on TEND benchmarks for natural language to MongoDB query generation.
DeepEye-SQL applies SDLC-inspired orchestration to Text-to-SQL, achieving 73.5% on BIRD-Dev, 75.07% on BIRD-Test, and 89.8% on Spider-Test with ~30B MoE models.
EviLink combines multi-hypothesis schema grounding with uncertainty-guided evidence acquisition, reporting 90.15% field-level recall and 123.30K average tokens on Spider2-Snow while improving downstream SQL generation.
A selection technique based on separating instances and provenance outperforms baselines for choosing among 2-3 NL2SQL candidates on a BIRD-DEV subset without consistency scores.
EGRefine optimizes column renamings via execution-grounded verification and view materialization to recover Text-to-SQL accuracy lost to schema naming issues while guaranteeing query equivalence.
N-rep consistency achieves comparable BIRD benchmark scores for text-to-SQL at $0.039 per query by combining multiple schema representations, without chain-of-thought reasoning or fine-tuning.
KaSLA applies knapsack optimization hierarchically to schema linking for LLM text-to-SQL, claiming better results than large models and improved SQL generation on Spider and BIRD.
XiYan-SQL achieves SOTA Text-to-SQL accuracy by combining schema filtering, a multi-generator ensemble fine-tuned on varied SQL formats, and a selection model.
CHESS deploys four LLM agents to retrieve information, prune schemas, generate refined SQL candidates, and validate via unit tests, reporting up to 71.10% accuracy on BIRD with 83% fewer calls than leading proprietary baselines.
An adaptive thresholding mechanism combined with sliding-window reranking retrieves a query-dependent number of tables from large corpora, improving retrieval and downstream text-to-SQL performance on Spider, BIRD, and Spider 2.0.
citing papers explorer
-
Same Data, Different Schemas: Robustness of LLM-based Text-to-SQL
A new evaluation framework generates equivalent schemas from an E/R model and shows that LLMs produce SQL queries with different answers across those schemas for fixed questions and data.
-
CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
CA-SQL achieves 51.72% execution accuracy on the challenging tier of the BIRD benchmark using GPT-4o-mini by scaling exploration breadth according to estimated task difficulty, evolutionary prompt seeding, and candidate voting.
-
EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL
EXPO-SQL improves Text-to-SQL by using clause-level rewards derived from execution error messages and incremental clause execution instead of uniform query-level rewards.
-
Draft-Refine-Optimize: Self-Evolved Learning for Natural Language to MongoDB Query Generation
EvoMQL uses iterative Draft-Refine-Optimize cycles with execution feedback to reach 76.6% accuracy on EAI and 83.1% on TEND benchmarks for natural language to MongoDB query generation.
-
DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework
DeepEye-SQL applies SDLC-inspired orchestration to Text-to-SQL, achieving 73.5% on BIRD-Dev, 75.07% on BIRD-Test, and 89.8% on Spider-Test with ~30B MoE models.
-
EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
EviLink combines multi-hypothesis schema grounding with uncertainty-guided evidence acquisition, reporting 90.15% field-level recall and 123.30K average tokens on Spider2-Snow while improving downstream SQL generation.
-
Data-aware candidate selection in NL2SQL translation via small separating instances
A selection technique based on separating instances and provenance outperforms baselines for choosing among 2-3 NL2SQL candidates on a BIRD-DEV subset without consistency scores.
-
EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement
EGRefine optimizes column renamings via execution-grounded verification and view materialization to recover Text-to-SQL accuracy lost to schema naming issues while guaranteeing query equivalence.
-
Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning
N-rep consistency achieves comparable BIRD benchmark scores for text-to-SQL at $0.039 per query by combining multiple schema representations, without chain-of-thought reasoning or fine-tuning.
-
Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation
KaSLA applies knapsack optimization hierarchically to schema linking for LLM text-to-SQL, claiming better results than large models and improved SQL generation on Spider and BIRD.
-
XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL
XiYan-SQL achieves SOTA Text-to-SQL accuracy by combining schema filtering, a multi-generator ensemble fine-tuned on varied SQL formats, and a selection model.
-
CHESS: Contextual Harnessing for Efficient SQL Synthesis
CHESS deploys four LLM agents to retrieve information, prune schemas, generate refined SQL candidates, and validate via unit tests, reporting up to 71.10% accuracy on BIRD with 83% fewer calls than leading proprietary baselines.
-
Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method
An adaptive thresholding mechanism combined with sliding-window reranking retrieves a query-dependent number of tables from large corpora, improving retrieval and downstream text-to-SQL performance on Spider, BIRD, and Spider 2.0.