Replacing Training with Memory: Listwise Selection for Text-to-SQL

• URL: http://arxiv.org/abs/2609.00834v1
• Date: Tue, 01 Sep 2026 07:35:00 GMT
• Title: Replacing Training with Memory: Listwise Selection for Text-to-SQL
• Abstract summary: We build reusable structured memories instead of learning selection behavior as model parameters.<n>We aggregate rankings across multiple input permutations, with inference cost optimized by execution results and pointwise scoring.<n>Across Text-to- benchmarks, it produces more stable selection without fine-tuning and fewer unnecessary comparisons than existing methods.
• Score: 34.25214572225323
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise selection, by jointly comparing multiple candidates, has been widely adopted, but fine-tuning listwise selectors is costly. We thus propose a fine-tuning-free listwise selector. We replace two major fine-tuning objectives with inference-time strategies: (1) learning selection criteria as ordering and (2) mitigating positional bias. First, we build reusable structured memories instead of learning selection behavior as model parameters. Given a question, MaP-SQL retrieves memories distilled from training data that encode how natural language maps to schema elements, SQL operations, and expected outputs. These memories serve as explicit decision criteria for evaluating candidates in a listwise manner. Second, to mitigate ordering bias of listwise selectors, we aggregate rankings across multiple input permutations, with inference cost optimized by execution results and pointwise scoring. Our approach improves selection accuracy while maintaining efficiency and compatibility with existing large language models. Across Text-to-SQL benchmarks, it produces more stable selection without fine-tuning and fewer unnecessary comparisons than existing methods. On BIRD-dev, it outperforms the previous state-of-the-art selector-based method R^3-SQL by 2.02 execution accuracy points on average using the same candidate sets, with 2.92x fewer tokens.

Related papers

• Residual Skill Optimization for Text-to-SQL Ensembles [37.13373780149542]
  We present DivSkill, a residual skill optimization framework that builds complementary agentic Text-to- ensembles without model fine-tuning.<n>Each new skill is optimized on examples the current skill ensemble fails on, provably targeting its marginal contribution to Pass@K.<n>On Spider2-Lite, DivSkill improves selected accuracy by up to +11.1 points on Snowflake and +8.3 on BigQuery over the strongest ensemble baseline.<n>Skills optimized a single dialect transfer without retraining across dialects (Snowflake, BigQuery, pts) and to a different task formulation, such as BIRD-Critic (+2.6)
  arXiv  Detail & Related papers  (2026-05-20T22:36:11Z)
• R$^3$-SQL: Ranking Reward and Resampling for Text-to-SQL [55.967050404665606]
  R$3$- achieves 75.03 execution accuracy on BIRD-dev, a new state of the art among methods using models with disclosed sizes, with consistent gains across five benchmarks.
  arXiv  Detail & Related papers  (2026-04-28T07:40:50Z)
• JudgeSQL: Reasoning over SQL Candidates with Weighted Consensus Tournament [26.476304887882133]
  Judge is a principled framework that redefines candidate selection through structured reasoning and weighted consensus tournament mechanism.<n>We show that Judge exhibits superior judgment capabilities and good cross-scale generalization and to generator capacity.
  arXiv  Detail & Related papers  (2025-10-17T11:46:38Z)
• A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL [20.010431872384714]
  We introduce XiYan, an innovative framework that employs a multi-context ensemble strategy to improve candidate generation.<n>We introduce M- schema, a semi-structured representation method designed to enhance the understanding of database structures.<n>Overall, our proposed XiYan-the-art framework achieves the state-of-the-art execution accuracy of 75.63% on Bird datasets benchmark.
  arXiv  Detail & Related papers  (2024-11-13T13:30:21Z)
• CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL [9.47170756607886]
  CHASE- is a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate generation and selection. To identify the best candidate, a selection agent is employed to rank the candidates through pairwise comparisons with a fine-tuned binary-candidates selection LLM. Overall, our proposed CHASE- achieves the state-of-the-art execution accuracy of 73.0% and 73.01% on the test set and development set of the notable BIRD Text-to- dataset benchmark.
  arXiv  Detail & Related papers  (2024-10-02T18:41:35Z)
• Using LLM to select the right SQL Query from candidates [7.462629286980003]
  We propose a re-rank method to select the right query from the candidate list. Experiment results show that the performance of some state-of-the-art models can get a 3.6% improvement after applying our re-rank method.
  arXiv  Detail & Related papers  (2024-01-04T07:50:24Z)
• SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data [54.69489315952524]
  "Prompt" is designed to improve the few-shot prompting capabilities of Text-to-LLMs. "Prompt" outperforms previous approaches for in-context learning with few labeled data by a large margin. We show that emphPrompt outperforms previous approaches for in-context learning with few labeled data by a large margin.
  arXiv  Detail & Related papers  (2023-11-06T05:24:06Z)
• UNITE: A Unified Benchmark for Text-to-SQL Evaluation [72.72040379293718]
  We introduce a UNIfied benchmark for Text-to-domain systems. It is composed of publicly available text-to-domain datasets and 29K databases. Compared to the widely used Spider benchmark, we introduce a threefold increase in SQL patterns.
  arXiv  Detail & Related papers  (2023-05-25T17:19:52Z)
• Wav2SQL: Direct Generalizable Speech-To-SQL Parsing [55.10009651476589]
  Speech-to-Spider (S2Spider) aims to convert spoken questions intosql queries given databases. We propose the first direct speech-to-speaker parsing model Wav2 which avoids error compounding across cascaded systems. Experimental results demonstrate that Wav2 avoids error compounding and achieves state-of-the-art results by up to 2.5% accuracy improvement over the baseline.
  arXiv  Detail & Related papers  (2023-05-21T19:26:46Z)
• Learning to Select from Multiple Options [48.59962245388264]
  Textual entailment (TE) has been shown as the state-of-the-art (SOTA) approach to dealing with selection problems. This work proposes a contextualized TE model (Context-TE) by appending other k options as the context of the current (P, H) modeling. Second, we speed up Context-TE by coming up with Parallel-TE, which learns the decisions of multiple options simultaneously.
  arXiv  Detail & Related papers  (2022-12-01T06:14:57Z)
• Photon: A Robust Cross-Domain Text-to-SQL System [189.1405317853752]
  We present Photon, a robust, modular, cross-domain NLIDB that can flag natural language input to which a mapping cannot be immediately determined. The proposed method effectively improves the robustness of text-to-native system against untranslatable user input.
  arXiv  Detail & Related papers  (2020-07-30T07:44:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.