Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Balloccu, Simone, Schmidtová, Patrícia, Lango, Mateusz, Dušek, Ondřej
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910340237754368
author Balloccu, Simone
Schmidtová, Patrícia
Lango, Mateusz
Dušek, Ondřej
author_facet Balloccu, Simone
Schmidtová, Patrícia
Lango, Mateusz
Dušek, Ondřej
contents Natural Language Processing (NLP) research is increasingly focusing on the use of Large Language Models (LLMs), with some of the most popular ones being either fully or partially closed-source. The lack of access to model details, especially regarding training data, has repeatedly raised concerns about data contamination among researchers. Several attempts have been made to address this issue, but they are limited to anecdotal evidence and trial and error. Additionally, they overlook the problem of \emph{indirect} data leaking, where models are iteratively improved by using data coming from users. In this work, we conduct the first systematic analysis of work using OpenAI's GPT-3.5 and GPT-4, the most prominently used LLMs today, in the context of data contamination. By analysing 255 papers and considering OpenAI's data usage policy, we extensively document the amount of data leaked to these models during the first year after the model's release. We report that these models have been globally exposed to $\sim$4.7M samples from 263 benchmarks. At the same time, we document a number of evaluation malpractices emerging in the reviewed papers, such as unfair or missing baseline comparisons and reproducibility issues. We release our results as a collaborative project on https://leak-llm.github.io/, where other researchers can contribute to our efforts.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03927
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs
Balloccu, Simone
Schmidtová, Patrícia
Lango, Mateusz
Dušek, Ondřej
Computation and Language
Artificial Intelligence
Natural Language Processing (NLP) research is increasingly focusing on the use of Large Language Models (LLMs), with some of the most popular ones being either fully or partially closed-source. The lack of access to model details, especially regarding training data, has repeatedly raised concerns about data contamination among researchers. Several attempts have been made to address this issue, but they are limited to anecdotal evidence and trial and error. Additionally, they overlook the problem of \emph{indirect} data leaking, where models are iteratively improved by using data coming from users. In this work, we conduct the first systematic analysis of work using OpenAI's GPT-3.5 and GPT-4, the most prominently used LLMs today, in the context of data contamination. By analysing 255 papers and considering OpenAI's data usage policy, we extensively document the amount of data leaked to these models during the first year after the model's release. We report that these models have been globally exposed to $\sim$4.7M samples from 263 benchmarks. At the same time, we document a number of evaluation malpractices emerging in the reviewed papers, such as unfair or missing baseline comparisons and reproducibility issues. We release our results as a collaborative project on https://leak-llm.github.io/, where other researchers can contribute to our efforts.
title Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.03927