REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval

• URL: http://arxiv.org/abs/2511.00805v1
• Date: Sun, 02 Nov 2025 05:01:04 GMT
• Title: REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval
• Abstract summary: REAR (Retrieve, Expand and Refine) is a three-stage framework for efficient, high-fidelity multi-table retrieval.<n>Rear retrieves query-aligned tables, expands these with structurally joinable tables, and refines them by pruning noisy or weakly related candidates.<n>Rear is retriever-agnostic and consistently improves dense/sparse retrievers on complex table QA datasets.
• Score: 46.38349148493421
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Answering natural language queries over relational data often requires retrieving and reasoning over multiple tables, yet most retrievers optimize only for query-table relevance and ignore table table compatibility. We introduce REAR (Retrieve, Expand and Refine), a three-stage, LLM-free framework that separates semantic relevance from structural joinability for efficient, high-fidelity multi-table retrieval. REAR (i) retrieves query-aligned tables, (ii) expands these with structurally joinable tables via fast, precomputed column-embedding comparisons, and (iii) refines them by pruning noisy or weakly related candidates. Empirically, REAR is retriever-agnostic and consistently improves dense/sparse retrievers on complex table QA datasets (BIRD, MMQA, and Spider) by improving both multi-table retrieval quality and downstream SQL execution. Despite being LLM-free, it delivers performance competitive with state-of-the-art LLM-augmented retrieval systems (e.g.,ARM) while achieving much lower latency and cost. Ablations confirm complementary gains from expansion and refinement, underscoring REAR as a practical, scalable building block for table-based downstream tasks (e.g., Text-to-SQL).

Related papers

• PEARL: Front-Loading Relational Chains for Multi-Hop Table Retrieval [15.811717493688812]
  PEARL is a training-free framework that shifts the paradigm toward vertical partitioning-based sub-table encoding.<n>PEARL augments the retrieval corpus offline by generating multi-hop queries over pre-identified join paths.<n>Experiments show that PEARL consistently outperforms existing methods, with up to +30.05% gains in R@2 on 3-hop queries.
  arXiv  Detail & Related papers  (2026-08-31T05:56:40Z)
• Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method [49.38787814788666]
  Existing table retrieval approaches select a pre-determined set of k tables with the highest similarity to the query.<n>The number of required tables varies across queries and cannot be known in advance.<n>We propose an adaptive table retrieval method that adjusts the number of tables retrieved according to the requirements of each query.
  arXiv  Detail & Related papers  (2026-04-12T14:53:56Z)
• FGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoning [9.827204445321147]
  Fine-Grained Multi-Table Retrieval FGTR is a new retrieval paradigm that employs a human-like reasoning strategy.<n> Experimental results show that FGTR outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-13T06:28:45Z)
• Fine-Grained Table Retrieval Through the Lens of Complex Queries [6.920588198594181]
  We present and study a table retrieval mechanism devising fine-grained typed query decomposition and global connectivity-awareness.<n>We evaluate the effectiveness of the two mechanisms through the lens of retrieval complexity which we measure along the axes of query- and data complexity.
  arXiv  Detail & Related papers  (2026-03-07T10:57:32Z)
• CGPT: Cluster-Guided Partial Tables with LLM-Generated Supervision for Table Retrieval [1.483000637348699]
  We introduce CGPT, a training framework that enhances table retrieval through LLM-generated supervision.<n>CGPT consistently outperforms retrieval baselines, including QGpT, with an average R@1 improvement of 16.54 percent.<n>Results indicate that semantically guided partial-table construction, combined with contrastive training from LLM-generated supervision, provides an effective and scalable paradigm for large-scale table retrieval.
  arXiv  Detail & Related papers  (2026-01-22T10:58:56Z)
• 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)
• Reasoning-enhanced Query Understanding through Decomposition and Interpretation [87.56450566014625]
  ReDI is a Reasoning-enhanced approach for query understanding through Decomposition and Interpretation.<n>We compiled a large-scale dataset of real-world complex queries from a major search engine.<n> Experiments on BRIGHT and BEIR demonstrate that ReDI consistently surpasses strong baselines in both sparse and dense retrieval paradigms.
  arXiv  Detail & Related papers  (2025-09-08T10:58:42Z)
• Improving Table Retrieval with Question Generation from Partial Tables [2.2169618382995764]
  We propose QGpT, a simple yet effective method that uses an LLM to generate synthetic questions based on small portions of a table.<n>The generated questions are then jointly embedded with the partial table segments used for generation, enhancing semantic alignment with user queries.
  arXiv  Detail & Related papers  (2025-08-08T09:35:56Z)
• Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance [8.83042313837811]
  We propose a graph-based framework that leverages human-curated relational knowledge to explicitly encode schema links and join paths.<n>Given a natural language query, our method searches on graph to construct interpretable reasoning chains, aided by pruning and sub-path merging strategies.<n>Experiments on both standard benchmarks and a realistic, large-scale dataset demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-06-04T20:21:52Z)
• Bridging Queries and Tables through Entities in Table Retrieval [70.13748256886288]
  Entities are well-studied in the context of text retrieval, but there is a noticeable lack of research on their applications in table retrieval.<n>We propose an entity-enhanced training framework and design an interaction paradigm based on entity representations.<n>Our proposed framework is plug-and-play and flexible, making it easy to integrate into existing table retriever training processes.
  arXiv  Detail & Related papers  (2025-04-09T03:16:33Z)
• RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking [63.253294691180635]
  In real-world scenarios, beyond pure text, a substantial amount of knowledge is stored in tables.<n>We first propose a table-corpora-aware RAG framework, named T-RAG, which consists of the hierarchical memory index, multi-stage retrieval, and graph-aware prompting.
  arXiv  Detail & Related papers  (2025-04-02T04:24:41Z)
• Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method [48.14236175156835]
  ARM aims to better align the question with the organization of the data collection by exploring relationships among data objects.<n>It outperforms standard RAG with query decomposition by up to 5.2 pt in execution accuracy and agentic RAG (ReAct) by up to 15.9 pt.<n>It achieves up to 5.5 pt and 19.3 pt higher F1 match scores compared to these approaches.
  arXiv  Detail & Related papers  (2025-01-30T18:07:19Z)

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.