Fine-Grained Table Retrieval Through the Lens of Complex Queries

About

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.

Wojciech Kosiuk, Xingyu Ji, Yeounoh Chung, Fatma Özcan, Madelon Hulsebos · 2026

Related benchmarks

Task	Dataset	Result
Text-to-SQL	Bird	Total Execution Accuracy66.56	68
Table Retrieval	BEAVER	Recall@1032.6	9
Table Retrieval	BEAVER	Capped Recall@2543.5	9
Table Retrieval	Bird	Capped Recall@2599.1	9
Retrieval	Bird	Recall@1094.2	9
Table Retrieval	FIBEN	Recall@1039.6	9
Table Retrieval	FIBEN	Capped Recall@2551.6	9
Table Retrieval	BEAVER	Recall@523.1	6
Table Retrieval	FIBEN	Recall@531.7	6
Table Retrieval	Bird	Recall@583.4	6