conftrace_

train-test leakage

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

entity contamination (1) minimum cut algorithm (1) performance overestimation (1) linear datamodel (1) dataset counterfactual (1) dataset splitting (1) scalable (1) adversarial test set (1) training data influence (1) f1 score (1)

Papers

Position: Graph Matching Systems Deserve Better Benchmarks ICML 2025 Random Splitting Negatively Impacts NER Evaluation: Quantifying and Eliminating the Overestimation of NER Performance ACL 2025 Datamodels: Understanding Predictions with Data and Data with Predictions ICML 2022