Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kocyigit, Muhammed Yusuf, Briakou, Eleftheria, Deutsch, Daniel, Luo, Jiaming, Cherry, Colin, Freitag, Markus
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910806908600320
author Kocyigit, Muhammed Yusuf
Briakou, Eleftheria
Deutsch, Daniel
Luo, Jiaming
Cherry, Colin
Freitag, Markus
author_facet Kocyigit, Muhammed Yusuf
Briakou, Eleftheria
Deutsch, Daniel
Luo, Jiaming
Cherry, Colin
Freitag, Markus
contents Data contamination -- the accidental consumption of evaluation examples within the pre-training data -- can undermine the validity of evaluation benchmarks. In this paper, we present a rigorous analysis of the effects of contamination on language models at 1B and 8B scales on the machine translation task. Starting from a carefully decontaminated train-test split, we systematically introduce contamination at various stages, scales, and data formats to isolate its effect and measure its impact on performance metrics. Our experiments reveal that contamination with both source and target substantially inflates BLEU scores, and this inflation is 2.5 times larger (up to 30 BLEU points) for 8B compared to 1B models. In contrast, source-only and target-only contamination generally produce smaller, less consistent over-estimations. Finally, we study how the temporal distribution and frequency of contaminated samples influence performance over-estimation across languages with varying degrees of data resources.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18771
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation
Kocyigit, Muhammed Yusuf
Briakou, Eleftheria
Deutsch, Daniel
Luo, Jiaming
Cherry, Colin
Freitag, Markus
Computation and Language
Artificial Intelligence
Data contamination -- the accidental consumption of evaluation examples within the pre-training data -- can undermine the validity of evaluation benchmarks. In this paper, we present a rigorous analysis of the effects of contamination on language models at 1B and 8B scales on the machine translation task. Starting from a carefully decontaminated train-test split, we systematically introduce contamination at various stages, scales, and data formats to isolate its effect and measure its impact on performance metrics. Our experiments reveal that contamination with both source and target substantially inflates BLEU scores, and this inflation is 2.5 times larger (up to 30 BLEU points) for 8B compared to 1B models. In contrast, source-only and target-only contamination generally produce smaller, less consistent over-estimations. Finally, we study how the temporal distribution and frequency of contaminated samples influence performance over-estimation across languages with varying degrees of data resources.
title Overestimation in LLM Evaluation: A Controlled Large-Scale Study on Data Contamination's Impact on Machine Translation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2501.18771