Problem
Research questions and friction points this paper is trying to address.
tabular reasoning
table retrieval
relational structure
cross-table semantics
PEARL: Front-Loading Relational Chains for Multi-Hop Table Retrieval
🤖 AI Summary
为解决表格检索中的跨表语义问题，提出PEARL框架，通过垂直分区子表编码和离线生成多跳查询来增强检索语料库，提高了多表检索的效率。
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
vertical partitioning
multi-hop queries
cross-table semantics
🔎 Similar Papers
No similar papers found.
