# HyST: LLM-Powered Hybrid Retrieval over Semi-Structured Tabular Data

arXiv: https://arxiv.org/abs/2508.18048 · HTML: https://mlsanity.com/paper/2508.18048/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 11 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Builds on (most cited first, 5 of 5)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Text2SQL is Not Enough: Unifying AI and Databases with TAG](https://mlsanity.com/paper/2408.14717/) (2024)
- [Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata](https://mlsanity.com/paper/2406.13213/) (2024)
- [SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models](https://mlsanity.com/paper/2311.09818/) (2023)

## Built on by (most cited first, 1 of 1)

- [Human Preference aligned Tabular Similarity](https://mlsanity.com/paper/2607.24880/) (2026)

## Abstract (arXiv)

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.