LogitTrace detects benchmark contamination by showing that contaminated inputs produce earlier stabilization in layerwise logit trajectories while clean inputs show more gradual accumulation.
arXiv preprint arXiv:2406.04197 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
ZCP detects direct and evasive data contamination in LLMs by truncating CoT reasoning and contrasting zero-CoT accuracy on original versus perturbed isomorphic datasets, plus a Contamination Confidence metric.
citing papers explorer
-
LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories
LogitTrace detects benchmark contamination by showing that contaminated inputs produce earlier stabilization in layerwise logit trajectories while clean inputs show more gradual accumulation.
-
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
ZCP detects direct and evasive data contamination in LLMs by truncating CoT reasoning and contrasting zero-CoT accuracy on original versus perturbed isomorphic datasets, plus a Contamination Confidence metric.