arXiv：cs.LG· Darian Lee, Shannon Rumsey, Jack St. Clair, Xinyi Tang, Aditya Bansal, Yuanming Shi·· 5 小时前AI 评分34
FALCON：面向 NL2SQL 的模型与数据集无关的合成数据生成框架
FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs
AI 导读
FALCON 是一个模型与数据库无关的 NL2SQL 合成数据生成框架，用紧凑开源模型低成本生成贴近真实基准复杂度的歧义感知数据。它结合 SQL 保留字种子与 persona 提示生成结构复杂查询，并用基于对齐的过滤区分真正错误与复杂但有效的查询。难度分层分析显示，查询越复杂，用 FALCON 数据训练的模型越优于基线，混合少量现有基准数据还能恢复简单查询性能。
正文
Abstract:Relational databases are among the most widely deployed forms of structured knowledge, and natural language access to them requires grounding language onto schema entities and relations while handling the ambiguity inherent in how people phrase requests. Existing synthetic NL-to-SQL data generation methods largely ignore this ambiguity and produce oversimplified queries that fail to prepare models for the complexity of real-world structured knowledge access. We present FALCON, a framework that generates realistic, ambiguity-aware NL-to-SQL data matching the complexity of challenging real-world benchmarks, at low cost using compact open models. Our approach combines reserved-word SQL seeding and persona-based prompting to generate structurally complex queries, while alignment-based filtering preserves difficulty by distinguishing genuinely incorrect examples from complex but valid queries. Human evaluation confirms consistent high quality across model sizes, and our generated data exceeds existing benchmarks in both SQL complexity and natural language richness. Difficulty-stratified analysis shows models trained on FALCON data increasingly outperform baseline-trained models as query complexity increases, validating our pipeline's success in generating challenging training data. When combined with a small proportion of existing benchmark data, mixed training recovers performance on simpler queries while preserving these advantages on complex ones. The model- and database-agnostic design enables organizations to generate high-complexity NL-to-SQL training data locally without external APIs.
| Comments: | Accepted to AKBC Workshop, EMNLP |
| Subjects: | Computation and Language (cs.CL); Databases (cs.DB); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.03625 [cs.CL] |
| (or arXiv:2610.03625v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03625 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Darian Lee [view email]
[v1]
Fri, 2 Oct 2026 17:19:50 UTC (911 KB)
来源：arXiv：cs.LG · arxiv.org