Efficient Record Linkage in the Age of Large Language Models: The Critical Role of Blocking

Algorithms, 2025

Recommended citation: N. Shah, S. Patiyara, J. Basak, S. Sahni, A. Mathur, K. Park, S. Rajasekaran. (2025). "Efficient Record Linkage in the Age of Large Language Models: The Critical Role of Blocking." Algorithms. https://doi.org/10.3390/a18110723

Studies blocking techniques for LLM-based record linkage, cutting the number of candidate pairs that need expensive LLM comparisons.

Authors: N. Shah, S. Patiyara, J. Basak, S. Sahni, A. Mathur, K. Park, S. Rajasekaran

Read the paper (DOI)