# Improving Table Retrieval with Question Generation from Partial Tables

arXiv: https://arxiv.org/abs/2508.06168 · HTML: https://mlsanity.com/paper/2508.06168/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2025.

## Built on by (most cited first, 5 of 5)

- [Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation](https://mlsanity.com/paper/2510.09671/) (2025)
- [Fine-Grained Table Retrieval Through the Lens of Complex Queries](https://mlsanity.com/paper/2603.07146/) (2026)
- [A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search](https://mlsanity.com/paper/2604.16394/) (2026)
- [PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries](https://mlsanity.com/paper/2605.18199/) (2026)
- [Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval](https://mlsanity.com/paper/2608.06614/) (2026)

## Abstract (arXiv)

Recent advances in open-domain question answering over tables have widely adopted large language models (LLMs) under the Retriever-Reader architecture. Prior works have effectively leveraged LLMs to tackle the complex reasoning demands of the Reader component, such as text-to-text, text-to-SQL, and multi hop reasoning. In contrast, the Retriever component has primarily focused on optimizing the query representation-training retrievers to retrieve relevant tables based on questions, or to select keywords from questions for matching table segments. However, little attention has been given to enhancing how tables themselves are represented in embedding space to better align with questions. To address this, we propose QGpT (Question Generation from Partial Tables), a simple yet effective method that uses an LLM to generate synthetic questions based on small portions of a table. These questions are generated to simulate how a user might query the content of the table currently under consideration. The generated questions are then jointly embedded with the partial table segments used for generation, enhancing semantic alignment with user queries. Without the need to embed entire tables, our method significantly improves retrieval performance across multiple benchmarks for both dense and late-interaction retrievers.