Generalized Entity Matching with Adaptivity via Large Language Models
Summary: GLEAM tackles unlabeled generalized entity matching with an LLM-guided structure/content graph, adaptive GMM–Bayesian candidate stopping, and hierarchical domain-aware reasoning. It improves F1 by up to 25.7% while reducing LLM calls across heterogeneous datasets.
(summarized by gpt-5.6-luna on Jul 26 2026)
@inproceedings{chen_sigmod26,
title = {{Generalized Entity Matching with Adaptivity via Large Language Models}},
author = {Chen, Xingguang and Shi, Yimin and Xiao, Xiaokui},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802066},
url = {https://dl.acm.org/doi/10.1145/3802066},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
Rank
Citing Paper
Year
Venue
Pagerank
PreviousPage 1 / 1Next
Outgoing Citations (Sorted by Pagerank)
Showing 14 of 14 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.