Mind the Data Gap: Bridging LLMs to Enterprise Data Integration
Summary: LLM-based integration methods trained on public corpora falter on enterprise “dark” data; current public benchmarks overestimate real-world performance. Presents the Goby Benchmark and three remedies—hierarchical annotation, runtime class-learning, and ontology synthesis—that restore LLM performance on enterprise integration to parity with public-data scenarios. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Moe Kayali (University of Washington)
- 2. Fabian Wenz (Massachusetts Institute of Technology; Technical University of Munich)
- 3. Nesime Tatbul (Intel; Massachusetts Institute of Technology)
- 4. Çağatay Demiralp (Amazon; Massachusetts Institute of Technology)
BibTeX Citation
@inproceedings{kayali_cidr25,
address = {Amsterdam, Netherlands},
series = {{CIDR} '25},
title = {{Mind the Data Gap: Bridging LLMs to Enterprise Data Integration}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Kayali, Moe and Wenz, Fabian and Tatbul, Nesime and Demiralp, Çağatay},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,906 | Unveiling Challenges for LLMs in Enterprise Data Engineering | 2026 | VLDB | 5.3483178e-05 |
| 10,125 | A Vision for Autonomous Data Agent Collaboration: From Query-by-Integration to Query-by-Collaboration | 2026 | CIDR | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 91 | WebTables: Exploring the Power of Tables on the Web | 2008 | VLDB | 0.00034838835 |
| 420 | Can Foundation Models Wrangle Your Data? | 2023 | VLDB | 0.00018789852 |
| 516 | Data Curation at Scale: The Data Tamer System | 2013 | CIDR | 0.00017171198 |
| 713 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB | 0.00014672521 |
| 1,923 | Annotating Columns with Pre-trained Language Models | 2022 | SIGMOD | 9.4789109e-05 |
| 2,242 | CHORUS: Foundation Models for Unified Data Discovery and Exploration | 2024 | VLDB | 8.8823802e-05 |
| 2,790 | GitTables: A Large-Scale Corpus of Relational Tables | 2023 | SIGMOD | 8.1200509e-05 |
| 7,038 | Towards NLP-Enhanced Data Profiling Tools | 2022 | CIDR | 5.7204576e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 2 | 10,733 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 3 | 10,510 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |
| 4 | 10,248 | Generalized Entity Matching with Adaptivity via Large Language Models | 2026 | SIGMOD |
| 5 | 9,310 | LLM-PBE: Assessing Data Privacy in Large Language Models | 2024 | VLDB |
| 6 | 3,536 | How Large Language Models Will Disrupt Data Management | 2023 | VLDB |
| 7 | 6,545 | DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models | 2024 | SIGMOD |
| 8 | 10,318 | In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration | 2026 | SIGMOD |
| 9 | 6,101 | LLM for Data Management | 2024 | VLDB |
| 10 | 8,906 | Unveiling Challenges for LLMs in Enterprise Data Engineering | 2026 | VLDB |