mlsanityData to 7 Oct 2026

Fine-Grained Table Retrieval Through the Lens of Complex Queries

arXiv 2603.07146 ↗First posted 7 Mar 2026cs.IR cs.AI cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Enabling question answering over tables and databases in natural language has become a key capability in the democratization of insights from tabular data sources. These systems first require retrieval of data that is relevant to a given natural language query, for which several methods have been introduced. In this work we present and study a table retrieval mechanism devising fine-grained typed query decomposition and global connectivity-awareness (DCTR), to handle the challenges induced by open-domain question answering over relational databases in complex usage contexts. 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. Our analyses over industry-aligned benchmarks illustrate the robustness of DCTR for highly composite queries and densely connected databases.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 31 references that are in the map. First posted on arXiv 7 Mar 2026.

Builds on

25 of 31 references.

References · 25

  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  2. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  3. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  4. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  5. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  6. 2024Jasper and Stella: distillation of SOTA embedding modelscited by 109
  7. 2025On the Theoretical Limitations of Embedding-Based Retrievalcited by 98
  8. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  9. 2024BEAVER: An Enterprise Benchmark for Text-to-SQLcited by 37
  10. 2025Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQLcited by 30
  11. 2024Is Table Retrieval a Solved Problem? Exploring Join-Aware Multi-Table Retrievalcited by 27
  12. 2025LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLcited by 26
13 more
  1. 2025Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End Systemcited by 22
  2. 2025TARGET: Benchmarking Table Retrieval for Generative Taskscited by 17
  3. 2025EnrichIndex: Using LLMs to Enrich Retrieval Indices Offlinecited by 15
  4. 2024Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queriescited by 12
  5. 2024FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmarkcited by 11
  6. 2024MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQLcited by 7
  7. 2025Improving Table Retrieval with Question Generation from Partial Tablescited by 5
  8. 2025GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprisecited by 4
  9. 2025RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQLcited by 4
  10. 2025Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQLcited by 4
  11. 2025Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrievalcited by 3
  12. 2025Are We Asking the Right Questions? On Ambiguity in Natural Language Queries for Tabular Data Analysiscited by 3
  13. 2025Exploring Multi-Table Retrieval Through Iterative Searchcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Toward Multi-Database Query Reasoning for Text2Cyphercited by 0