GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation

Ekata Mitra; Yufei Tao; Kamalamalini Nagasundaram; Ameeta Agrawal

cs.CLNov 2, 2026

GRIPS: An Empirical Study of Pre-SQL Grounding Information for SQL Generation

Authors: Ekata Mitra, Yufei Tao, Kamalamalini Nagasundaram, Ameeta Agrawal

Organizations: Department of Computer Science, Portland State University, USA

Abstract

Text-to-SQL systems answer natural language questions over structured data, but can fail before SQL generation by linking question mentions to the wrong table, column, value, or relation. Even valid SQL can then return an incorrect answer. This raises a central question: What pre-SQL information helps a SQL generator, and when does additional information cease to help? We investigate this question on TempTabQA-C and BIRD. Among the audited SQL Static failures, grounding errors form the largest category on both benchmarks. We introduce GRIPS (Grounding Representation and Input Processing for SQL generation), a three-stage method that derives structured pre-SQL information to make these decisions explicit before query generation. Across GPT-5-nano and Llama-70B, GRIPS-Adaptive improves over SQL Static in 18 of 20 settings, with an average accuracy gain of 11.8 percentage points, while reducing model-call token usage by 47.8%. Our controlled analysis shows which grounding information can improve SQL generation, whereas adding more pre-SQL information does not consistently help. By separating question-input grounding from SQL generation, GRIPS makes text-to-SQL more accurate, efficient, and easier to diagnose.

Figures & tables

Example 1: TempTabQA-C, Hard
C:	Darrell Pace
	Personal Information: Birth Date = 1956-10-23
	Olympic Games: Individual MedalGold $\mid$ 1976 $\mid$ Montreal; MedalGold $\mid$ 1984 $\mid$ Los Angeles
	Pan American Games: Team MedalGold $\mid$ 1979 $\mid$ San Juan; MedalGold $\mid$ 1983 $\mid$ Caracas
	Pan American Games: Individual MedalGold $\mid$ 1983 $\mid$ Caracas; MedalSilver $\mid$ 1979 $\mid$ San Juan
Q:	How many medals did Darrell Pace win in his/her twenties?

Table 1: Examples from TempTabQA-C and BIRD where C: Table Context; Q: Question; A: Answer; E: Evidence.

Figure 1: SQL Static failure breakdown by diagnostic class and subcategory. TempTabQA-C grounding errors concentrate on schema-slice and cardinality (G5/G3); BIRD on filter and join grounding (G2/G4).

Figure 2: Overview of GRIPS pipeline. Stage I maps the question and context to a structured pre-SQL record using a frozen benchmark-specific rule-set. Stage II combines the original input, the Stage I record, and SQL demonstrations to generate SQL query. Stage III normalizes and executes the query to produce the final answer.

Panel of Table 3 — Table 3: Stage I outputs for the running examples in Table 1 .

Panel of Figure 3 — Figure 3: Controlled comparison of Stage I information under a fixed Stage II generator. The first four conditions vary the amount of information; the last three vary its source. G+P denotes guided representation with prediction_trace , and G+FK denotes guided representation with verified foreign-key paths.

Figure 4: Share of SQL Static failures rescued by GRIPS , by diagnostic class and subcategory.

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 5: Failure composition by diagnostic class after re-auditing SQL Static errors on TempTabQA-C (Easy/Medium/Hard) and BIRD (Simple/Moderate/Challenging).

Panel of Figure 6 — Figure 6: Concrete Stage I–Stage II projections for the examples in Table 1

Panel of Figure 7 — Figure 7: Stage II prompt structure. The benchmark input and Stage I information vary by condition; the task, demonstrations, current question, and output contract are held fixed in controlled comparisons.

Figure 8: Share of SQL Static failures rescued by GRIPS , by diagnostic class and subcategory.

Control	Condition	Definition	Illustrative example
Shared	Without Stage I information	The auxiliary Stage I block is empty. The question, schema/evidence, demonstrations, and SQL-generation instructions remain unchanged.	Empty payload: {} .
Shared	With guided representation	Supplies recognized question–input matches with their semantic types and normalized values. No profile summaries are included.	Column: element Tables: bond , atom .
Content	With representation + profile	Adds deterministic counts, structural scope, priority, target determinacy, and coarse difficulty summaries. This is the deployed GRIPS handoff.	Representation: element , bond , atom Implicated tables: 2 FK span: 2 Target: clear; difficulty: moderate.
Content	With expanded profile	Adds internal pattern, count/repetition, requirement, and compressed-signature fields to the deployed handoff.	Pattern: column over two tables Repeated table mentions: 4 Requirement: 5-tuple Signature: repeated-table doublet.
Source	With adapted DIN links	Supplies schema links produced by the DIN-SQL linking stage to the common Stage II generator. This is an adapted intermediate output, not native end-to-end DIN-SQL.	connected.bond_id = TR004_8_9 connected.atom_id = atom.atom_id Selected column: atom.element .
Source	With adapted MAC selection	Supplies the MAC-SQL selector’s table and column decisions to the common Stage II generator. The base schema remains available.	Keep: atom , bond Select from connected : bond and atom IDs Drop: molecule .

Appendix

Table 17: Reader-facing definitions and examples of the controlled Stage I information conditions. Examples are condensed from the BIRD question “What elements are in the TR004_8_9 bond atoms?” The first two conditions are shared across comparisons. Content conditions cumulatively add information, whereas source conditions substitute alternative Stage I information under the same Stage II generator.

Text-to-SQL

Text-to-SQL translates natural-language questions into executable database queries, linking user intent to schemas, values, and SQL logic.

See all 185 papers

DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation
Aug 12, 2026Anik Pramanik, Murat Kantarcioglu, Vincent Oria +1LLM Prompting Schema Linking
New Jersey Institute of Technology, USA. · Virginia Tech, USA.
EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge
Jun 2, 2026Chengxi Liao, Tao Xu, Zulong Chen +7LLM Grounding Text-to-SQL
1HKUST (GZ) · 2Alibaba Group · 4Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) +1
ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL
Jun 4, 2026Xiaobing Chen, Ai Jian, Eryu Guo +1Execution-Guided Code Generation Schema Linking
Harbin Engineering University, Harbin, China · Harbin Institute of Technology, Harbin, China · Beijing University of Posts and Telecommunications, Beijing, China

Aug 12, 2026J/K move · Enter open · S save

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

Anik Pramanik, Murat Kantarcioglu, Vincent Oria, Shantanu Sharma

New Jersey Institute of Technology, USA. · Virginia Tech, USA.

LLM Prompting Schema Linking Text-to-SQL Database Systems

Open paper AskPDF arXiv

Prompting-based (i.e., non-fine-tuning) Text-to-SQL methods, where underlying large language model parameters are not changed for the task, face three problems: (i) relying on coarse-grained schema information that may not reveal the fine-grained relationships needed to distinguish ambiguous columns, (ii) failing to capture recurring SQL-generation failures, and (iii) suffering from omission or hallucination of components in complex questions. This paper develops DexterSQL, a prompting/non-fine-tuning-based Text-to-SQL system that improves SQL generation with three novel components: (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, (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 (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. DexterSQL achieves a higher accuracy compared to the state-of-the-art using both open-source/weight and closed-source/weight models. Particularly, DexterSQL shows a high improvement of at least 5.5% using an open-weight model (GPT-OSS-120B) on BIRDDev, with total accuracy 70.4%. DexterSQL also shows better improvement of at least 1.4% using closed-weight models, with total accuracy 72.1% and 72.9% on BIRD-Dev with GPT-4o and GPT-5.2.

Abstract

Text-to-SQL

Explore similar work

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

EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge

ACE-SQL: Adaptive Co-Optimization via Empirical Credit Assignment for Text-to-SQL