Data Contamination Report from the 2024 CONDA Shared Task

TL;DR

This paper reports on the first shared task of the CONDA 2024 workshop, which collected and documented evidence of data contamination in NLP datasets and models to help the community understand and mitigate this issue.

Contribution

It introduces a structured, public database of data contamination instances in NLP, based on community contributions, to aid research and evaluation integrity.

Findings

566 contamination entries documented

91 contaminated sources identified

23 contributors participated

Abstract

The 1st Workshop on Data Contamination (CONDA 2024) focuses on all relevant aspects of data contamination in natural language processing, where data contamination is understood as situations where evaluation data is included in pre-training corpora used to train large scale models, compromising evaluation results. The workshop fostered a shared task to collect evidence on data contamination in current available datasets and models. The goal of the shared task and associated database is to assist the community in understanding the extent of the problem and to assist researchers in avoiding reporting evaluation results on known contaminated resources. The shared task provides a structured, centralized public database for the collection of contamination evidence, open to contributions from the community via GitHub pool requests. This first compilation paper is based on 566 reported entries over 91 contaminated sources from a total of 23 contributors. The details of the individual contamination events are available in the platform. The platform continues to be online, open to contributions from the community.