# Single and Multi Truth Data Fusion using Large Language Models

arXiv: https://arxiv.org/abs/2606.28062 · HTML: https://mlsanity.com/paper/2606.28062/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [A Survey on Truth Discovery](https://mlsanity.com/paper/1505.02463/) (2015)
- [Magneto: Combining Small and Large Language Models for Schema Matching](https://mlsanity.com/paper/2412.08194/) (2024)
- [DeepJoin: Joinable Table Discovery with Pre-trained Language Models](https://mlsanity.com/paper/2212.07588/) (2022)
- [Truth Finding on the Deep Web: Is the Problem Solved?](https://mlsanity.com/paper/1503.00303/) (2015)
- [Unveiling Challenges for LLMs in Enterprise Data Engineering](https://mlsanity.com/paper/2504.10950/) (2025)
- [UniDM: A Unified Framework for Data Manipulation with Large Language Models](https://mlsanity.com/paper/2405.06510/) (2024)
- [TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations](https://mlsanity.com/paper/2411.17110/) (2024)
- [Table Integration in Data Lakes Unleashed: Pairwise Integrability Judgment, Integrable Set Discovery, and Multi-Tuple Conflict Resolution](https://mlsanity.com/paper/2412.00324/) (2024)
- [Automatic End-to-End Data Integration using Large Language Models](https://mlsanity.com/paper/2603.10547/) (2026)
- [Taxonomy Inference for Tabular Data Using Large Language Models](https://mlsanity.com/paper/2503.21810/) (2025)

## Abstract (arXiv)

Data fusion, also known as truth discovery, is a data integration problem that aims to determine the correct value or set of values for each attribute of an object when presented with potentially conflicting values from multiple sources. Data fusion tasks belong to two main categories: single-truth scenarios, where each attribute has only one correct value, and multi-truth scenarios, where multiple values can be valid simultaneously. This paper investigates the use of Large Language Models (LLMs) in data fusion tasks for tabular data. Various prompting strategies, encompassing both single-truth and multi-truth scenarios, are investigated empirically. Domain-dependent, domain-independent, zero-shot and one-shot prompts are evaluated on three different benchmark datasets. Experimental results demonstrate that LLM-based approaches outperform traditional unsupervised truth discovery methods, such as DART and LTM, across all datasets. The codebase of this study has been made publicly available on GitHub.