User queries in real-world recommendation systems often combine structured constraints (e.g., category, attributes) with unstructured preferences (e.g., product descriptions or reviews). We introduce HyST (Hybrid retrieval over Semi-structured Tabular data), a hybrid retrieval framework that combines LLM-powered structured filtering with semantic embedding search to support complex information needs over semi-structured tabular data. HyST extracts attribute-level constraints from natural language using large language models (LLMs) and applies them as metadata filters, while processing the remaining unstructured query components via embedding-based retrieval. Experiments on a semi-structured benchmark show that HyST consistently outperforms tradtional baselines, highlighting the importance of structured filtering in improving retrieval precision, offering a scalable and accurate solution for real-world user queries.
@article{arxiv.2508.18048,
title = {HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data},
author = {Jiyoon Myung and Jihyeon Park and Joohyung Han},
journal= {arXiv preprint arXiv:2508.18048},
year = {2025}
}
Comments
Accepted at the 2nd EARL Workshop on Evaluating and Applying Recommender Systems with Large Language Models (RecSys 2025)