REVIEW 13 cited by
A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
To tackle the challenges of large language model performance in natural language to SQL tasks, we introduce XiYan-SQL, an innovative framework that employs a multi-generator ensemble strategy to improve candidate generation. We introduce M-Schema, a semi-structured schema representation method designed to enhance the understanding of database structures. To enhance the quality and diversity of generated candidate SQL queries, XiYan-SQL integrates the significant potential of in-context learning (ICL) with the precise control of supervised fine-tuning. On one hand, we propose a series of training strategies to fine-tune models to generate high-quality candidates with diverse preferences. On the other hand, we implement the ICL approach with an example selection method based on named entity recognition to prevent overemphasis on entities. The refiner optimizes each candidate by correcting logical or syntactical errors. To address the challenge of identifying the best candidate, we fine-tune a selection model to distinguish nuances of candidate SQL queries. The experimental results on multiple dialect datasets demonstrate the robustness of XiYan-SQL in addressing challenges across different scenarios. Overall, our proposed XiYan-SQL achieves the state-of-the-art execution accuracy of 75.63% on Bird benchmark, 89.65% on the Spider test set, 69.86% on SQL-Eval, 41.20% on NL2GQL. The proposed framework not only enhances the quality and diversity of SQL queries but also outperforms previous methods.
Forward citations
Cited by 13 Pith papers
-
Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL
An evolving Vulnerability Codex plus hypothesis-driven perturbations exposes latent Text-to-SQL failures in LLMs far better than fixed expert rules, with transferable patterns and early remediation gains.
-
VirtualSet: Typed Ontology Worlds as an LLM Generation Target for Grounded Queries and Guarded Decisions
A typed ontology-expression target for LLMs beat glossary-matched direct SQL on BIRD (67.5% vs 63.5%) and intercepted all 20 hallucinated action bodies in a 30-body corpus.
-
ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement
A fine-tuned model with special error tokens detects SQL mistakes and guides LLMs to fix them, raising execution accuracy on BIRD from 55.87% to 66.23% and on Spider from 75.44% to 86.94% over GPT-4o.
-
RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL
RASL retrieves relevant tables and columns for text-to-SQL by decomposing schemas into semantic entities, calibrating entity-type importance on training data, and using an LLM to rank candidates, beating baselines on ...
-
SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generation
SEED automatically generates evidence from database schemas, descriptions, and sampled values, improving text-to-SQL accuracy in no-evidence settings.
-
SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes
SDE-SQL improves text-to-SQL accuracy by having the model generate and execute exploratory SQL probes to learn database contents before and while writing the final query.
-
TailorSQL: An NL2SQL System Tailored to Your Query Workload
Adding workload-derived hints and tailored retrieval from past SQL queries improves NL2SQL execution accuracy and reduces prompt size on three benchmarks.
-
Automatic Metadata Extraction for Text-to-SQL
LLM-generated summaries of database profiling statistics outperform human-written metadata for text-to-SQL on BIRD, and a SQL-generation-based schema linker adds further gains.
-
QUEST: Query Optimization in Unstructured Document Analysis
QUEST reduces LLM extraction cost in unstructured document analytics by retrieving only relevant segments via a two-level index and by generating per-document filter and join execution plans during query execution.
-
Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages
Generating Python programs as intermediate guidance before SQL, then voting on Python execution results to select the fastest matching SQL, improves text-to-SQL execution accuracy and efficiency on BIRD and Archer.
-
Effectiveness of Prompt Optimization in NL2SQL Systems
Iterative prompt optimization with an LLM proposer improves NL2SQL accuracy and prompt compactness on BIRD dev, and a latency-aware variant reduces worst-case SQL execution time.
-
LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning
The authors built a 4,038-question text-to-SQL benchmark with chain-of-thought annotations and found that state-of-the-art models reach only 33.20% execution accuracy.
-
CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation
A 7B model trained with GRPO and a sparse execution-correctness reward reaches 59.97% execution accuracy on BIRD dev, though the evaluation protocol and baseline numbers contain inconsistencies.
Discussion (0). Continue with ORCID to comment.