Data Contamination Calibration for Black-box LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Wentao, Hu, Jiaqi, Li, Liyao, Wang, Haobo, Chen, Gang, Zhao, Junbo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911900103606272
author Ye, Wentao
Hu, Jiaqi
Li, Liyao
Wang, Haobo
Chen, Gang
Zhao, Junbo
author_facet Ye, Wentao
Hu, Jiaqi
Li, Liyao
Wang, Haobo
Chen, Gang
Zhao, Junbo
contents The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size. However, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination, i.e. the benchmark data is used for training. In this work, we propose a holistic method named Polarized Augment Calibration (PAC) along with a new to-be-released dataset to detect the contaminated data and diminish the contamination effect. PAC extends the popular MIA (Membership Inference Attack) -- from machine learning community -- by forming a more global target at detecting training data to Clarify invisible training data. As a pioneering work, PAC is very much plug-and-play that can be integrated with most (if not all) current white- and black-box LLMs. By extensive experiments, PAC outperforms existing methods by at least 4.5%, towards data contamination detection on more 4 dataset formats, with more than 10 base LLMs. Besides, our application in real-world scenarios highlights the prominent presence of contamination and related issues.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11930
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data Contamination Calibration for Black-box LLMs
Ye, Wentao
Hu, Jiaqi
Li, Liyao
Wang, Haobo
Chen, Gang
Zhao, Junbo
Machine Learning
The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size. However, the unchecked ultra-large-scale training sets introduce a series of potential risks like data contamination, i.e. the benchmark data is used for training. In this work, we propose a holistic method named Polarized Augment Calibration (PAC) along with a new to-be-released dataset to detect the contaminated data and diminish the contamination effect. PAC extends the popular MIA (Membership Inference Attack) -- from machine learning community -- by forming a more global target at detecting training data to Clarify invisible training data. As a pioneering work, PAC is very much plug-and-play that can be integrated with most (if not all) current white- and black-box LLMs. By extensive experiments, PAC outperforms existing methods by at least 4.5%, towards data contamination detection on more 4 dataset formats, with more than 10 base LLMs. Besides, our application in real-world scenarios highlights the prominent presence of contamination and related issues.
title Data Contamination Calibration for Black-box LLMs
topic Machine Learning
url https://arxiv.org/abs/2405.11930