Alignment-Guided Largest Table Overlap Size Estimation
Quick Answer
This paper shows that ALORE, a new overlap ratio estimator, significantly outperforms the state-of-the-art Armadillo by reducing MAE by up to 55% overall and 69% in zero-shot transfer, while achieving up to 89x speedup.
Quick Take
ALORE, a new overlap ratio estimator, significantly outperforms the state-of-the-art Armadillo by reducing MAE by up to 55% overall and 69% in zero-shot transfer, while achieving up to 89x speedup. It addresses challenges in heterogeneous table repositories by explicitly representing row-column structures and exposing inter-table alignment signals. ALORE's effectiveness is validated across diverse datasets, enhancing query-by-table retrieval.
Key Points
- ALORE reduces MAE by up to 55% and 69% in zero-shot transfer.
- Achieves up to 89x speedup compared to existing methods.
- Utilizes a Two-View Row-Column Hypergraph encoder for better structure representation.
- Exposes inter-table alignment signals during training without costly searches.
- Demonstrated effectiveness across diverse datasets and real-world corpus.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Fast estimation of the size of the largest overlap between tables enables blocking and query-by-table retrieval in large table repositories. The first and the state-of-the-art estimator Armadillo improves efficiency by embedding each table independently and approximating overlap ratio via embedding similarity. However, accurate estimation in heterogeneous repositories remains limited by three challenges: (C1) overlap depends on row-column structure, i.e., each matched cell must preserve both its row and column membership under a joint alignment of the two tables, but existing encodings leave this structure to be inferred indirectly; (C2) independent encoding provides no explicit channel for inter-table alignment signals, biasing prediction toward global similarity; (C3) naive value encodings overfit to corpus-specific distributions, causing cross-domain degradation. Hence, we propose ALORE, a scalable and domain-robust overlap ratio estimator built on three principles: (P1) explicitly represent row-column structure; (P2) expose inter-table alignment signals during training without expensive alignment search; (P3) reduce sensitivity to corpus-specific value distributions. ALORE instantiates these principles with a Two-View Row-Column Hypergraph encoder, alignment-guided objectives with inexpensive interaction signals, and a domain-robust value mapping. Experiments on multiple datasets spanning diverse domains and scales, including a large real-world corpus beyond prior benchmarks, show that ALORE outperforms the state of the art. ALORE reduces MAE by up to 55% overall and 69% in zero-shot transfer, while achieving up to 89x speedup. We further validate its effectiveness for query-by-table retrieval.
| Comments: | Accepted/to appear at SIGMOD 2027 |
| Subjects: | Computation and Language (cs.CL); Databases (cs.DB) |
| Cite as: | arXiv:2607.03049 [cs.CL] |
| (or arXiv:2607.03049v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.03049 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ge Lee [view email]
[v1]
Fri, 3 Jul 2026 07:38:43 UTC (3,960 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Quantifying Prior Dominance in Systems
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.