arXiv Machine Learning
Correcting test set contamination by spiking the training data
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 10
Spiking the training data to correct for test set contamination
arXiv:2605. 24818v2 Announce Type: replace-cross Abstract: The literature on test set contamination largely focuses on detection, but the correction of contaminated test scores is underexplored.
arXiv Computation and Language
Sep 4
Contamination Inflates Scores but Rarely Reorders Large Language Model Leaderboards
The paper investigates how benchmark contamination—leakage of test items into training data—affects large language model (LLM) leaderboards. By comparing original test items with semantically equivalent paraphrases, the authors measure contamination as a violation of anchor-item invariance and find that it inflates absolute scores but rarely changes model rankings. Across 47 public models and 74 finetuned models on four benchmarks, the rank correlation between standard and paraphrase-controlled leaderboards is 0.997, with only a handful of cases showing differential contamination that could alter rankings.
arXiv Machine Learning
Jul 1
Probing Memorization of Tabular In-Context Learning
arXiv:2606. 31208v1 Announce Type: new Abstract: Large tabular models (LTMs), i.
arXiv AI
Aug 6
When Large Language Models Know the Table: A Framework for Assessing Data Contamination in Tabular Datasets
arXiv:2510. 20351v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly exposed to data contamination, i.
arXiv Machine Learning
Aug 5
Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores
arXiv:2608. 02985v1 Announce Type: new Abstract: The standard check for contamination in LLM backtests is simple: compare scores before and after the training cutoff.
arXiv Machine Learning
Sep 10
The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
The paper uncovers a hidden flaw in evaluating machine unlearning on BatchNorm-based models: a single forward pass over retained data can alter the model’s normalization state without changing weights, misleadingly restoring performance. This effect, formalized as a weight‑preserving fixed‑point operator, shows that apparent forgetting can be entirely due to BatchNorm running statistics, not to the unlearning method itself. Experiments demonstrate that the artifact can inflate forget accuracy by up to 78 percentage points across nine methods, and that switching to GroupNorm eliminates the problem.