Cross-domain experiments show that the learned scorer transfers across benchmarks, indicating that the method captures reusable joingraph traversal behavior.
Abstract
Retrieving the right tables is a prerequisite for Text-to-SQL over realistic databases. Dense table retrievers rank schema elements independently, but this ignores a key source of evidence: some required tables are not mentioned in the question and become identifiable only through their join relationships to already relevant tables. We introduce JOINGR, a join-aware table retrieval method that treats the database join graph as the retrieval space. Columns are represented as graph nodes, while intra-table and foreign-key relationships are represented as typed edges. Given a question, JOINGR selects semantically similar anchor tables, traverses join edges with a query-conditioned scorer, and aggregates the resulting edge deposits into table scores. The scorer is a lightweight MLP on top of frozen query, node, and edge embeddings, trained with a pairwise margin loss over gold tables. On BIRD and Spider datasets, JOINGR is competitive with the strongest retrieval baselines. On BEAVER, a challenging enterprise benchmark with multi-hop table requirements, JOINGR substantially improves recall over dense retrieval and re-ranking baselines. Cross-domain experiments show that the learned scorer transfers across benchmarks, indicating that the method captures reusable joingraph traversal behavior.
Recent advancements in large language models have introduced new capabilities for reasoning over structured data, particularly through program-aided tools that can analyze tables. However, many existing methods address single-table scenarios or assume that the relevant tables are already provided. In practice, users of...
Prince Larbi Ampofo, Ryoji Kubo, D. Difallah· Volume 1· 0 citations
PEARL augments the retrieval corpus offline by generating multi-hop queries over pre-identified join paths and reorganizing relevant columns into vertically partitioned corpus units, enabling effective multi-table retrieval without query-time LLM inference.
S. Ho, Hyeongu Kang, Seongku Kang et al.· 0 citations
TABERTA is presented, a unified retrieval framework for dataset discovery that adapts a bi-encoder language model to relational data by fine-tuning it on serialized representations of tables by fine-tuning the language encoder to diverse structural patterns using optimized strategies that serialize schema and table con...
Enas Khwaileh, L. Traeger, Albert Gatt et al.· International Conference on...· 0 citations
This work evaluates representative join discovery methods spanning set-based, feature-based, and learned approaches, together with general-purpose language-model embedding baselines, and publicly release the processed datasets, ground-truth annotations, and generation pipeline to facilitate reproducible evaluation and...
Graph with Adaptive Shortcuts (GAS), a framework that leverages historical query logs to build lightweight auxiliary structures, enhancing search efficiency over a single base graph with minimal overhead, and consistently outperforms existing general indexes in wide-table scenarios.
Zi-Yuan He, Yu-Xiang Wang, Yu Sun et al.· Proceedings of the VLDB Endo...· 0 citations
JEVDB is presented, a scalable semantic database system that uses fast, typed decision models for semantic filters, joins, classification, and ranking, while selectively escalating uncertain cases to generative LLMs.