Data Contamination: From Memorization to Exploitation

Inbal Magar, Roy Schwartz


Abstract
Pretrained language models are typically trained on massive web-based datasets, which are often “contaminated” with downstream test sets. It is not clear to what extent models exploit the contaminated data for downstream tasks. We present a principled method to study this question. We pretrain BERT models on joint corpora of Wikipedia and labeled downstream datasets, and fine-tune them on the relevant task. Comparing performance between samples seen and unseen during pretraining enables us to define and quantify levels of memorization and exploitation.Experiments with two models and three downstream tasks show that exploitation exists in some cases, but in others the models memorize the contaminated data, but do not exploit it. We show that these two measures are affected by different factors such as the number of duplications of the contaminated data and the model size. Our results highlight the importance of analyzing massive web-scale datasets to verify that progress in NLP is obtained by better language understanding and not better data exploitation.
Anthology ID:
2022.acl-short.18
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
157–165
Language:
URL:
https://aclanthology.org/2022.acl-short.18
DOI:
10.18653/v1/2022.acl-short.18
Bibkey:
Cite (ACL):
Inbal Magar and Roy Schwartz. 2022. Data Contamination: From Memorization to Exploitation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 157–165, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Data Contamination: From Memorization to Exploitation (Magar & Schwartz, ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-short.18.pdf
Video:
 https://aclanthology.org/2022.acl-short.18.mp4
Code
 schwartz-lab-nlp/data_contamination
Data
SST