[2603.07146] Fine-Grained Table Retrieval Through the Lens of Complex Queries
Abstract: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.
Fine-Grained Table Retrieval Through the Lens of Complex Queries Wojciech Kosiuk1 , Xingyu Ji2 , Yeounoh Chung3 , Fatma Özcan3 , Madelon Hulsebos4 * 1 University of Amsterdam, 2 UC Berkeley, 3 Google, 4 CWI Abstract sition for table retrieval, single-hop retrieval using Enabling question…
saved by
related reading
- Metadata-driven Table Union Search: Leveraging Semantics for Restricted Access Data Integrationarxiv.org
- Retrieve, Merge, Predict: Augmenting Tables with Data Lakeshal.science
- 182789martoranabnwdefdpr - 68d3e689349be.pdfresearch.vu.nl
- Analysis of Open Government Datasets From a Data Design and Integration Perspectiveopenproceedings.org
- Putting Task Expertise into RL Achieves State-of-the-Art Performance on Text-to-SQLthinkingmachines.ai
- Voyage AI | Homevoyageai.com
- Better RAG 3: The text is your friendolickel.com
- Advanced Retriever Techniques to Improve Your RAGs | Towards Data Sciencetowardsdatascience.com
- A More Human Approach To Databasesccorcos.github.io
- Auto-Retrieval from a Vector Databasegpt-index.readthedocs.io
- Chroma Context-1: Training a Self-Editing Search Agent | Chromatrychroma.com
- [2508.21038] On the Theoretical Limitations of Embedding-Based Retrievalarxiv.org