LasRepair++ pairs an LLM instructor with an SLM corrector, refines context via EM, and down-weights uncertain repairs using column-calibrated confidence, reporting 18.1% average F1 gain over baselines on data repair tasks.
InProceedings of the International Conference on Management of Data (SIGMOD)
3 Pith papers cite this work, alongside 178 external citations. Polarity classification is still indexing.
3
Pith papers citing it
178
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Introduces Bayesian Membership Privacy (BMP) as a sampling-aware node-level privacy definition for GNNs quantified by posterior membership probability, plus an auditing method and benchmark experiments.
A new catalog classifying 35 data error types into missing, incorrect, and redundant categories for tabular data, with definitions and examples to improve data quality management.
citing papers explorer
-
Collaborative Large and Small Language Models for Accurate and Scalable Data Repair
LasRepair++ pairs an LLM instructor with an SLM corrector, refines context via EM, and down-weights uncertain repairs using column-calibrated confidence, reporting 18.1% average F1 gain over baselines on data repair tasks.
-
Bayesian Membership Privacy for Graph Neural Networks
Introduces Bayesian Membership Privacy (BMP) as a sampling-aware node-level privacy definition for GNNs quantified by posterior membership probability, plus an auditing method and benchmark experiments.
-
A Catalog of Data Errors
A new catalog classifying 35 data error types into missing, incorrect, and redundant categories for tabular data, with definitions and examples to improve data quality management.