@inproceedings{chen-etal-2025-benchmarking-large,
title = "Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation",
author = "Chen, Simin and
Chen, Yiming and
Li, Zexin and
Jiang, Yifan and
Wan, Zhongwei and
He, Yixin and
Ran, Dezhi and
Gu, Tianle and
Li, Haizhou and
Xie, Tao and
Ray, Baishakhi",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.511/",
pages = "10091--10109",
ISBN = "979-8-89176-332-6",
abstract = "In the era of evaluating large language models (LLMs), data contamination has become an increasingly prominent concern. To address this risk, LLM benchmarking has evolved from a *static* to a *dynamic* paradigm. In this work, we conduct an in-depth analysis of existing *static* and *dynamic* benchmarks for evaluating LLMs. We first examine methods that enhance *static* benchmarks and identify their inherent limitations. We then highlight a critical gap{---}the lack of standardized criteria for evaluating *dynamic* benchmarks. Based on this observation, we propose a series of optimal design principles for *dynamic* benchmarking and analyze the limitations of existing *dynamic* benchmarks.This survey provides a concise yet comprehensive overview of recent advancements in data contamination research, offering valuable insights and a clear guide for future research efforts. We maintain a GitHub repository to continuously collect both static and dynamic benchmarking methods for LLMs. The repository can be found at this link."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2025-benchmarking-large">
<titleInfo>
<title>Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zexin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongwei</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dezhi</namePart>
<namePart type="family">Ran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianle</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haizhou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baishakhi</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>In the era of evaluating large language models (LLMs), data contamination has become an increasingly prominent concern. To address this risk, LLM benchmarking has evolved from a *static* to a *dynamic* paradigm. In this work, we conduct an in-depth analysis of existing *static* and *dynamic* benchmarks for evaluating LLMs. We first examine methods that enhance *static* benchmarks and identify their inherent limitations. We then highlight a critical gap—the lack of standardized criteria for evaluating *dynamic* benchmarks. Based on this observation, we propose a series of optimal design principles for *dynamic* benchmarking and analyze the limitations of existing *dynamic* benchmarks.This survey provides a concise yet comprehensive overview of recent advancements in data contamination research, offering valuable insights and a clear guide for future research efforts. We maintain a GitHub repository to continuously collect both static and dynamic benchmarking methods for LLMs. The repository can be found at this link.</abstract>
<identifier type="citekey">chen-etal-2025-benchmarking-large</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.511/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>10091</start>
<end>10109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation
%A Chen, Simin
%A Chen, Yiming
%A Li, Zexin
%A Jiang, Yifan
%A Wan, Zhongwei
%A He, Yixin
%A Ran, Dezhi
%A Gu, Tianle
%A Li, Haizhou
%A Xie, Tao
%A Ray, Baishakhi
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F chen-etal-2025-benchmarking-large
%X In the era of evaluating large language models (LLMs), data contamination has become an increasingly prominent concern. To address this risk, LLM benchmarking has evolved from a *static* to a *dynamic* paradigm. In this work, we conduct an in-depth analysis of existing *static* and *dynamic* benchmarks for evaluating LLMs. We first examine methods that enhance *static* benchmarks and identify their inherent limitations. We then highlight a critical gap—the lack of standardized criteria for evaluating *dynamic* benchmarks. Based on this observation, we propose a series of optimal design principles for *dynamic* benchmarking and analyze the limitations of existing *dynamic* benchmarks.This survey provides a concise yet comprehensive overview of recent advancements in data contamination research, offering valuable insights and a clear guide for future research efforts. We maintain a GitHub repository to continuously collect both static and dynamic benchmarking methods for LLMs. The repository can be found at this link.
%U https://aclanthology.org/2025.emnlp-main.511/
%P 10091-10109
Markdown (Informal)
[Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation](https://aclanthology.org/2025.emnlp-main.511/) (Chen et al., EMNLP 2025)
ACL
- Simin Chen, Yiming Chen, Zexin Li, Yifan Jiang, Zhongwei Wan, Yixin He, Dezhi Ran, Tianle Gu, Haizhou Li, Tao Xie, and Baishakhi Ray. 2025. Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 10091–10109, Suzhou, China. Association for Computational Linguistics.