Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval

• URL: http://arxiv.org/abs/2607.13311v1
• Date: Tue, 14 Jul 2026 22:31:55 GMT
• Title: Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval
• Abstract summary: We recast five text-to-language datasets as retrieval tasks at both table and column granularity.<n>We show that off-the-shelf text and code embedders transfer poorly to this setting.<n>We propose corpus-adaptive fine-tuning: natural-language queries are synthesized directly from the target corpus.
• Score: 9.741583305127994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval in the SQL setting has largely been studied as the task of finding, within a large collection of SQL statements, the statement that answers a natural-language question. At scale, however, a more fundamental retrieval problem precedes generation: schema retrieval, identifying the tables and columns a question requires in a database that may contain thousands of them, far more than fit in a model's context. We argue that this step warrants first-class evaluation. To this end, we recast five text-to-SQL datasets (Spider, BIRD, BEAVER, and two LiveSQLBench variants) as retrieval tasks at both table and column granularity, covering realistic and enterprise-scale schemas under two document representations, and we show that off-the-shelf text and code embedders transfer poorly to this setting. We then propose corpus-adaptive fine-tuning: natural-language queries are synthesized directly from the target schema corpus, granularity-aware hard negatives are mined, and a 305M-parameter embedder is fine-tuned contrastively. This procedure raises average recall@10 from 60.4 to 75.6 (nDCG@10 from 51.9 to 68.0), making the 305M model the strongest retriever under one billion parameters and competitive with state-of-the-art embedders of 4-8B parameters, more than an order of magnitude larger. The same recipe improves an 8B state-of-the-art embedder from 77.8 to 78.4 recall@10, matching the best result on the benchmark and indicating that the adaptation is backbone-agnostic. Leave-one-corpus-out experiments and a leakage audit show that these gains reflect a transferable schema-retrieval ability rather than memorization of the evaluation data. Our results establish schema linking as a standalone retrieval task and lightweight, label-free corpus adaptation as a practical route to deploying it at enterprise scale.

Related papers

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows [54.49251107006261]
  We introduce Spider 2.0-AIFunc, a benchmark of 465 verified instances across 125 real-world databases covering six types of AI functions on the Snowflake platform.<n>We find that the strongest proprietary models reach 67-70% execution accuracy while the best open-source model achieves 58.1%.
  arXiv  Detail & Related papers  (2026-07-07T12:54:08Z)
• Database Context Compression for Text-to-SQL on Real-World Large Databases [23.20528827913883]
  We argue that the main bottleneck is no longer reasoning, but database representation.<n>Real databases contain repeated audit columns, large groups of similar tables, opaque identifiers whose meanings are stored only in documentation, and extensive data dictionaries with little query-relevant information.<n>We reformulate the problem as database context compression, a query-alinking transformation that rewrites schemas, semantic descriptions, and external documentation into a compact representation.
  arXiv  Detail & Related papers  (2026-06-26T20:49:46Z)
• DecoSearch: Complexity-Aware Routing and Plan-Level Repair for Text-to-SQL [21.568773170643084]
  DecoSearch is a training-free framework that routing each query to the appropriate level of reasoning effort.<n>It achieves 70.53% execution accuracy on BIRD and 88.31% on Spider with a DeepSeek backbone.
  arXiv  Detail & Related papers  (2026-06-16T11:48:50Z)
• EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement [10.675982676332941]
  Existing approaches treat schemas as fixed and address errors downstream.<n>We frame schema refinement as a constrained optimization problem.<n>We analyze the computational hardness of this problem, which motivates a column-wise greedy decomposition.
  arXiv  Detail & Related papers  (2026-05-01T13:01:59Z)
• TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas [22.65474240295148]
  We propose TRUST- (Truthful Reasoning with Unknown via Tools)<n>We formulate the task as a Partially Observable Markov Decision Process where our autonomous agent employs a structured four-phase protocol to ground reasoning in verified.<n>By applying token-level masked advantages, this strategy isolates exploration rewards from execution outcomes to resolve credit assignment.
  arXiv  Detail & Related papers  (2026-03-17T12:30:42Z)
• CORE-T: COherent REtrieval of Tables for Text-to-SQL [91.76918495375384]
  CORE-T is a scalable, training-free framework that enriches tables with purpose metadata and pre-computes a lightweight table-compatibility cache.<n>Across Bird, Spider, and MMQA, CORE-T improves table-selection F1 by up to 22.7 points while retrieving up to 42% fewer tables.
  arXiv  Detail & Related papers  (2026-01-19T14:51:23Z)
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation [54.53145282349042]
  We introduce DSR-sourced, a textbfDual-textbfS textbfReasoning framework that models Text-to-context as an interaction between an adaptive context state and a progressive generation state.<n>Without any post-training or in-context examples, DSR-sourced achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set.
  arXiv  Detail & Related papers  (2025-11-26T13:52:50Z)
• SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension [77.93156509994994]
  We show how to represent short chunks in a way that is conditioned on a broader context window to enhance retrieval performance.<n>Existing embedding models are not well-equipped to encode such situated context effectively.<n>Our method substantially outperforms state-of-the-art embedding models.
  arXiv  Detail & Related papers  (2025-08-03T23:59:31Z)
• RAISE: Reasoning Agent for Interactive SQL Exploration [47.77323087050061]
  We propose a novel framework that unifies schema linking, query generation, and iterative refinement within a single, end-to-end component.<n>Our method emulates how humans answer questions when working with unfamiliar databases.
  arXiv  Detail & Related papers  (2025-06-02T03:07:08Z)
• RSL-SQL: Robust Schema Linking in Text-to-SQL Generation [51.00761167842468]
  We propose a novel framework called RSL- that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. benchmarks demonstrate that our approach achieves SOTA execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on GPT-4ocorrection. Our approach outperforms a series of GPT-4 based Text-to-Seek systems when adopting DeepSeek (much cheaper) with same intact prompts.
  arXiv  Detail & Related papers  (2024-10-31T16:22:26Z)
• BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval [54.54576644403115]
  We introduce BRIGHT, the first text retrieval benchmark that requires intensive reasoning to retrieve relevant documents.<n>Our dataset consists of 1,384 real-world queries spanning diverse domains, such as economics, psychology, mathematics, and coding.<n>We show that incorporating explicit reasoning about the query improves retrieval performance by up to 12.2 points.
  arXiv  Detail & Related papers  (2024-07-16T17:58:27Z)
• N-Best Hypotheses Reranking for Text-To-SQL Systems [6.966624873109535]
  Text-to- task maps natural language utterances to structured queries. State-of-the-art (SOTA) systems rely on finetuning large, pre-trained language models. Findings show significant potential improvements with reranking.
  arXiv  Detail & Related papers  (2022-10-19T15:35:06Z)

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.