DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation

arXiv:2608.11889v1 Announce Type: cross Abstract: Prompting-based (extit{i}.extit{e}., non-fine-tuning) Text-to-SQL methods, where underlying large language model parameters are not changed for the task, face three problems: (extit{i})~relying on coarse-grained schema information that may not reveal the fine-grained relationships needed to distinguish ambiguous columns, (extit{ii})~not capturing recurring SQL-generation failures, and (extit{iii})~suffering from omission, hallucination, or misplacement of conditions in complex questions. This paper develops extsc{DexterSQL}, a prompting/non-fine-tuning-based Text-to-SQL system that improves SQL generation with three novel components: (extit{i})~deep schema explorator that identifies ambiguous columns, analyzes their individual and joint data distributions to uncover their relationships and the distinct role of each, (extit{ii})~database-agnostic rule creator that mines mismatches between generated and gold SQL only on the training database and converts them into database-agnostic corrective rules that capture recurring LLM failure patterns; and (extit{iii})~multi-path SQL generation that introduces a dependency-tree-based intermediate representation that uses the question's sentence structure to guide its decomposition into an SQL skeleton for final SQL generation. extsc{DexterSQL} achieves a higher accuracy compared to the state-of-the-art using both open-source/weight and closed-source/weight models. Particularly, extsc{DexterSQL}'s shows a high improvement of at least 2.7% using an open-weight model (GPT-OSS-120B) on BIRD-Dev, with total accuracy 67.6%. extsc{DexterSQL} also shows better improvement of at least 0.9% using closed-weight models, with total accuracy 71.6% and 72.2% on BIRD-Dev with GPT-4o and GPT-5.2.

Source: arXiv cs.AI | 2026-08-13