mlsanityData to 14 Oct 2026

Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method

arXiv 2605.18766 ↗First posted 12 Apr 2026cs.IR cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Retrieving relevant tables from extensive databases for a given natural language query is essential for accurately answering questions in tasks such as text-to-SQL. Existing table retrieval approaches select a pre-determined set of k tables with the highest similarity to the query. However, the number of required tables varies across queries and cannot be known in advance. Enforcing a fixed number of retrieved tables regardless of the query may either retrieve an undersized set, failing to obtain all necessary evidence, or retrieve an oversized pool, including irrelevant tables. To address this issue, we propose an adaptive table retrieval method that adjusts the number of tables retrieved according to the requirements of each query. Specifically, we utilize an adaptive thresholding mechanism to selectively retrieve tables and integrate a sliding-window reranking algorithm to efficiently process a large table corpus. Extensive experiments on Spider, BIRD, and Spider 2.0 demonstrate that our method effectively addresses the limitations of the top-k retrieval strategy, improving performance in retrieval and downstream tasks. Our code and data are available at https://github.com/sbY99/Adaptive-Table-Retrieval.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 12 Apr 2026.

Builds on

29 of 39 references.

References · 29

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  7. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  8. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 554
  9. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  10. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  11. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  12. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 307
17 more
  1. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
  2. 2022SGPT: GPT Sentence Embeddings for Semantic Searchcited by 204
  3. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 155
  4. 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
  5. 2021Open Domain Question Answering over Tables via Dense Retrievalcited by 74
  6. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 54
  7. 2024BEAVER: An Enterprise Benchmark for Text-to-SQLcited by 42
  8. 2024Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLMcited by 35
  9. 2024Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigmcited by 31
  10. 2024Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrievalcited by 27
  11. 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasonerscited by 25
  12. 2021Retrieving Complex Tables with Multi-Granular Graph Representation Learningcited by 24
  13. 2023CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQLcited by 24
  14. 2025Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End Systemcited by 23
  15. 2025DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankerscited by 9
  16. 2024MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQLcited by 7
  17. 2025Tailoring Table Retrieval from a Field-aware Hybrid Matching Perspectivecited by 7

Built on by

Not cited yet.