GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models

• URL: http://arxiv.org/abs/2509.01308v2
• Date: Wed, 29 Oct 2025 14:09:33 GMT
• Title: GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models
• Abstract summary: Outcome Reward Models (ORMs) assign utility scores to generated outputs based on semantic correctness.<n>We propose a unified framework for training ORMs tailored to the Text-to-Spider task.
• Score: 16.184651199160882
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-SQL, the task of translating natural language questions into SQL queries, has significantly advanced with the introduction of Large Language Models (LLMs), broadening database accessibility for a wide range of users. Despite substantial progress in generating valid SQL, current LLMs still struggle with complex queries. To address this limitation, test-time strategies such as Best-of-N (BoN) and Majority Voting (Maj) are often employed, based on the assumption that LLMs can produce correct answers after multiple attempts. However, these methods rely on surface-level heuristics, selecting the syntactically correct query through execution-based BoN (ex-BoN) or the most frequently generated one through Majority Voting. Recently, Outcome Reward Models (ORMs), which assign utility scores to generated outputs based on semantic correctness, have emerged as a promising reinforcement learning approach for improving model alignment. We argue that ORMs could serve as an effective new test-time heuristic, although their application in this context remains largely underexplored. In this work, we propose a unified framework for training ORMs tailored to the Text-to-SQL task and assess their effectiveness as a test-time heuristic within the BoN strategy. We benchmark ORMs against ex-BoN and Maj across the BIRD and Spider datasets, fine-tuning diverse open-source LLMs from the Qwen2, Granite3, and Llama3 families. Results show that ORMs outperform ex-BoN and Maj, achieving execution accuracy gains of +4.33% (BIRD) and +2.10% (Spider) over ex-BoN, and +2.91% (BIRD) and +0.93% (Spider) over Maj. We further demonstrate that finetuning models already aligned with SQL generation, such as OmniSQL, yields superior ORM performance. Additionally, we observe that ORMs achieve competitive results on simple queries and benefit more from an increased number of candidates compared to ex-BoN and Maj.

Related papers

• Test-Time Verification for Text-to-SQL via Outcome Reward Models [16.184651199160882]
  We study Outcome Models (ORMs) as learned semantic scoring functions for testtime verification.<n>ORM-based selection consistently outperforms execution-based Best-of-N and Majority Voting, with gains of up to +4.33% on BIRD and +2.10% on Spider.
  arXiv  Detail & Related papers  (2026-06-29T19:31:39Z)
• FINER-SQL: Boosting Small Language Models for Text-to-SQL [40.19592881059662]
  Large language models suffer from high computational cost, long latency, and data privacy concerns.<n>A natural alternative is to use small language models, which enable efficient and private on-premise deployment.<n>We propose FINER-sql, a scalable and reusable reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-05-05T07:51:29Z)
• SLM-SQL: An Exploration of Small Language Models for Text-to-SQL [0.0]
  Small language models (SLMs) offer inherent advantages in inference speed and suitability for edge deployment.<n>We leverage recent advancements in post-training techniques to explore Textto- applications.<n> Experimental results validate the effectiveness and generalizability of our method.
  arXiv  Detail & Related papers  (2025-07-30T08:29:07Z)
• Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models [22.960560371494832]
  Small language models (SLMs) struggle with NL2 tasks, exhibiting poor performance and incompatibility with existing frameworks.<n>We introduce Feather- Paradigm, a new lightweight framework tailored for SLMs.<n>The proposed paradigm raises the accuracy ceiling of SLMs to 54.76%, highlighting its effectiveness.
  arXiv  Detail & Related papers  (2025-03-22T16:22:53Z)
• Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation [25.638927795540454]
  We introduce the Text-to-No task, which aims to convert natural language queries into accessible queries.<n>To promote research in this area, we released a large-scale and open-source dataset for this task, named TEND (short interfaces for Text-to-No dataset)<n>We also designed a SLM (Small Language Model)-assisted and RAG (Retrieval-augmented Generation)-assisted multi-step framework called SMART, which is specifically designed for Text-to-No conversion.
  arXiv  Detail & Related papers  (2025-02-16T17:01:48Z)
• MCTS-SQL: Light-Weight LLMs can Master the Text-to-SQL through Monte Carlo Tree Search [1.166711394125328]
  Text-to-OTA is a fundamental yet challenging task in the NLP area.<n>We propose MCTS-OTA, a novel framework that uses Monte Carlo Tree Search.<n>We propose a token-level prefixcache mechanism that stores prior information during iterations.
  arXiv  Detail & Related papers  (2025-01-28T00:52:23Z)
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows [64.94146689665628]
  Spider 2.0 is an evaluation framework for real-world text-to-sql problems derived from enterprise-level database use cases.<n>The databases in Spider 2.0 are sourced from real data applications, often containing over 1,000 columns and stored in local or cloud database systems such as BigQuery and Snowflake.<n>We show that solving problems in Spider 2.0 frequently requires understanding and searching through database metadata, dialect documentation, and even project-levels.
  arXiv  Detail & Related papers  (2024-11-12T12:52:17Z)
• PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL [54.304872649870575]
  Large Language Models (LLMs) have emerged as powerful tools for Text-to-sense tasks. In this study, we propose that employing query group partitioning allows LLMs to focus on learning the thought processes specific to a single problem type.
  arXiv  Detail & Related papers  (2024-09-21T09:33:14Z)
• Relational Database Augmented Large Language Model [59.38841050766026]
  Large language models (LLMs) excel in many natural language processing (NLP) tasks. They can only incorporate new knowledge through training or supervised fine-tuning processes. This precise, up-to-date, and private information is typically stored in relational databases.
  arXiv  Detail & Related papers  (2024-07-21T06:19:10Z)
• RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL [48.516004807486745]
  Large language models (LLMs) with in-context learning have significantly improved the performance of text-to- task. We propose RB-, a novel retrieval-based framework for in-context prompt engineering. Experiment results demonstrate that our model achieves better performance than several competitive baselines on public datasets BIRD and Spider.
  arXiv  Detail & Related papers  (2024-07-11T08:19:58Z)
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation [76.76046657162306]
  Large language models (LLMs) have emerged as a new paradigm for Text-to- task. Large language models (LLMs) have emerged as a new paradigm for Text-to- task.
  arXiv  Detail & Related papers  (2023-08-29T14:59:54Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)
• 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)
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs [89.68522473384522]
  We present Bird, a big benchmark for large-scale database grounded in text-to-efficient tasks. Our emphasis on database values highlights the new challenges of dirty database contents. Even the most effective text-to-efficient models, i.e. ChatGPT, achieves only 40.08% in execution accuracy.
  arXiv  Detail & Related papers  (2023-05-04T19:02:29Z)

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.