PEARL: Front-Loading Relational Chains for Multi-Hop Table Retrieval
2026-08-31 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors address the difficulty of finding useful tables for answering questions that require combining information across multiple tables. Instead of looking at whole tables, they split tables into smaller parts based on columns related by joins and prepare these parts in advance for quicker searching. Their method, called PEARL, improves the ability to retrieve relevant data from multiple tables without needing big computations during the search. Experiments show that their approach works better than previous methods, especially for complex queries requiring multiple steps.
large language modelstabular reasoningtable retrievaljoin relationshipsvertical partitioningmulti-hop queriessub-table encodinginformation retrievalR@2 metriccorpus augmentation
Authors
Subeen Ho, Hyeongu Kang, SeongKu Kang, Susik Yoon
Abstract
While large language models (LLMs) have shown strong capabilities in tabular reasoning, retrieving relevant tables remains challenging due to the fragmented and relational structure of real-world data. Existing work typically relies on whole table representations that overlook cross-table semantics induced by join relationships. We propose PEARL, a training-free framework that shifts the paradigm toward vertical partitioning-based sub-table encoding. 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. Experiments show that PEARL consistently outperforms existing methods, with up to +30.05% gains in R@2 on 3-hop queries. The source code is available at https://github.com/SOOB2NHO/PEARL.