PEARL: Front-Loading Relational Chains for Multi-Hop Table Retrieval
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.
Create a lesson
Related papers
Closed Forms and Synthetic Twins: Predicting Approximate Nearest Neighbor Recall from Embedding Statistics
Shmuel Herman
MUSES: A Benchmark for Prospective Intellectual-Roots Retrieval
Rohan Pandey, Sunjae Kwon, Hong Yu
Two-Sided State-Space Models for Sequential Recommendation with Non-Random Multimodal Review Feedback
Ziwen Pan, Zihan Liang, Ruoxuan Xiong
MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval
Seokwon Song, Sohyeon Kim, Gunhee Kim
Learning from What You Retrieve: Online RL Fine-Tuning for Semantic Retrieval
Shaowei Wei, Chong Huang, Songtao Fang et al.
Generative Retrieval for E-commerce: Jointly Learning Embedding and Codebook with Same Product Cluster
Songtao Fang, Zihao Xu, Shaowei Wei et al.