Contaminating pre-training data with full source-target translation test pairs inflates BLEU scores, much more for 8B models than 1B models, while partial contamination has smaller and less consistent effects.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation
Contaminating pre-training data with full source-target translation test pairs inflates BLEU scores, much more for 8B models than 1B models, while partial contamination has smaller and less consistent effects.