# Solo: Data Discovery Using Natural Language Questions Via A Self-Supervised Approach

arXiv: https://arxiv.org/abs/2301.03560 · HTML: https://mlsanity.com/paper/2301.03560/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jan 2023.

## Built on by (most cited first, 11 of 11)

- [Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System](https://mlsanity.com/paper/2504.09207/) (2025)
- [TARGET: Benchmarking Table Retrieval for Generative Tasks](https://mlsanity.com/paper/2505.11545/) (2025)
- [Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI](https://mlsanity.com/paper/2407.21523/) (2024)
- [Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees](https://mlsanity.com/paper/2509.02896/) (2025)
- [Empowering Tabular Data Preparation with Language Models: Why and How?](https://mlsanity.com/paper/2508.01556/) (2025)
- [ENCO: Life-Cycle Management of Enterprise-Grade Copilots](https://mlsanity.com/paper/2412.06099/) (2024)
- [DataScout: Automatic Data Fact Retrieval for Statement Augmentation with an LLM-Based Agent](https://mlsanity.com/paper/2504.17334/) (2025)
- [Emergent evaluation hubs in a decentralizing large language model ecosystem](https://mlsanity.com/paper/2510.01286/) (2025)
- [RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching](https://mlsanity.com/paper/2604.22758/) (2026)
- [PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries](https://mlsanity.com/paper/2605.18199/) (2026)
- [Alignment-Guided Largest Table Overlap Size Estimation](https://mlsanity.com/paper/2607.03049/) (2026)

## Abstract (arXiv)

Most deployed data discovery systems, such as Google Datasets, and open data portals only support keyword search. Keyword search is geared towards general audiences but limits the types of queries the systems can answer. We propose a new system that lets users write natural language questions directly. A major barrier to using this learned data discovery system is it needs expensive-to-collect training data, thus limiting its utility. In this paper, we introduce a self-supervised approach to assemble training datasets and train learned discovery systems without human intervention. It requires addressing several challenges, including the design of self-supervised strategies for data discovery, table representation strategies to feed to the models, and relevance models that work well with the synthetically generated questions. We combine all the above contributions into a system, Solo, that solves the problem end to end. The evaluation results demonstrate the new techniques outperform state-of-the-art approaches on well-known benchmarks. All in all, the technique is a stepping stone towards building learned discovery systems. The code is open-sourced at https://github.com/TheDataStation/solo