# Mind the Data Gap: Bridging LLMs to Enterprise Data Integration

arXiv: https://arxiv.org/abs/2412.20331 · HTML: https://mlsanity.com/paper/2412.20331/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 29 Dec 2024.

## Builds on (most cited first, 12 of 12)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Deduplicating Training Data Mitigates Privacy Risks in Language Models](https://mlsanity.com/paper/2202.06539/) (2022)
- [Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools](https://mlsanity.com/paper/2405.20362/) (2024)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?](https://mlsanity.com/paper/2308.10168/) (2023)
- [Investigating Data Contamination in Modern Benchmarks for Large Language Models](https://mlsanity.com/paper/2311.09783/) (2023)
- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)
- [Grammar-Aligned Decoding](https://mlsanity.com/paper/2405.21047/) (2024)
- [GitTables: A Large-Scale Corpus of Relational Tables](https://mlsanity.com/paper/2106.07258/) (2021)
- [Annotating Columns with Pre-trained Language Models](https://mlsanity.com/paper/2104.01785/) (2021)
- [VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository](https://mlsanity.com/paper/1905.04616/) (2019)
- [CHORUS: Foundation Models for Unified Data Discovery and Exploration](https://mlsanity.com/paper/2306.09610/) (2023)

## Built on by (most cited first, 7 of 7)

- [Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs](https://mlsanity.com/paper/2601.17058/) (2026)
- [LLM-Powered Proactive Data Systems](https://mlsanity.com/paper/2502.13016/) (2025)
- [Exploring Differences Between Tabular Enterprise Data and Public Benchmarks](https://mlsanity.com/paper/2606.30452/) (2026)
- [SINT-Flow: Schema Integration using Large Language Model Workflows](https://mlsanity.com/paper/2607.24492/) (2026)
- [NGDBench: Towards Neural Graph Data Management](https://mlsanity.com/paper/2603.05529/) (2026)
- [Lazy or Efficient? Towards Accessible Eye-Tracking Event Detection Using LLMs](https://mlsanity.com/paper/2604.13243/) (2026)
- [X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention](https://mlsanity.com/paper/2605.15505/) (2026)

## Abstract (arXiv)

Leading large language models (LLMs) are trained on public data. However, most of the world's data is dark data that is not publicly accessible, mainly in the form of private organizational or enterprise data. We show that the performance of methods based on LLMs seriously degrades when tested on real-world enterprise datasets. Current benchmarks, based on public data, overestimate the performance of LLMs. We release a new benchmark dataset, the GOBY Benchmark, to advance discovery in enterprise data integration. Based on our experience with this enterprise benchmark, we propose techniques to uplift the performance of LLMs on enterprise data, including (1) hierarchical annotation, (2) runtime class-learning, and (3) ontology synthesis. We show that, once these techniques are deployed, the performance on enterprise data becomes on par with that of public data. The Goby benchmark can be obtained at https://goby-benchmark.github.io/.