Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding
Summary: Cents unifies LLM-based table-understanding tasks in a flexible framework, rather than task-specific systems. Its tabular-input compression reduces token cost while improving accuracy, outperforming prior LLM baselines across tasks at equal or lower cost. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Guorui Xiao (University of Washington)
- 2. Dong He (University of Washington)
- 3. Jin Wang (Arizona State University)
- 4. Magdalena Balazinska (University of Washington)
BibTeX Citation
@article{xiao_vldb25,
title = {{Cents: A Flexible and Cost-Effective Framework for LLM-Based Table Understanding}},
author = {Xiao, Guorui and He, Dong and Wang, Jin and Balazinska, Magdalena},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {4574--4587},
doi = {10.14778/3749646.3749714},
url = {https://doi.org/10.14778/3749646.3749714},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,287 | Shape-Agnostic Table Overlap Discovery: A Maximum Common Subhypergraph Approach | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 18 of 18 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,736 | Sentence to Model: Cost-Effective Data Collection LLM Agent | 2025 | SIGMOD |
| 2 | 6,545 | DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models | 2024 | SIGMOD |
| 3 | 1,923 | Annotating Columns with Pre-trained Language Models | 2022 | SIGMOD |
| 4 | 2,099 | Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks | 2024 | SIGMOD |
| 5 | 10,318 | In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration | 2026 | SIGMOD |
| 6 | 10,856 | Optimized Batch Prompting for Cost-effective LLMs | 2025 | VLDB |
| 7 | 9,505 | TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations | 2025 | VLDB |
| 8 | 8,829 | Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees | 2026 | SIGMOD |
| 9 | 10,733 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 10 | 8,627 | ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries | 2025 | VLDB |