English
Related papers

Related papers: Estimating Contamination via Perplexity: Quantifyi…

200 papers

CDD, or Contamination Detection via output Distribution, identifies data contamination by measuring the peakedness of a model's sampled outputs. We study the conditions under which this approach succeeds and fails on small language models…

Artificial Intelligence · Computer Science 2026-03-12 Omer Sela

Identifying anomalies and contamination in datasets is important in a wide variety of settings. In this paper, we describe a new technique for estimating contamination in large, discrete valued datasets. Our approach considers the normal…

Information Theory · Computer Science 2015-06-16 Matthew L. Malloy , Scott Alfeld , Paul Barford

Hampering the interpretation of benchmark scores, evaluation data contamination has become a growing concern in the evaluation of LLMs, and an active area of research studies its effects. While evaluation data contamination is easily…

Computation and Language · Computer Science 2024-11-07 Aaditya K. Singh , Muhammed Yusuf Kocyigit , Andrew Poulton , David Esiobu , Maria Lomeli , Gergely Szilvasy , Dieuwke Hupkes

In machine learning, contamination refers to situations where testing data leak into the training set. The issue is particularly relevant for the evaluation of the performance of Large Language Models (LLMs), which are generally trained on…

Computation and Language · Computer Science 2025-06-23 Nicolas Yax , Pierre-Yves Oudeyer , Stefano Palminteri

Data contamination hinders fair LLM evaluation by introducing test data into newer models' training sets. Existing studies solve this challenge by updating benchmarks with newly collected data. However, they fail to guarantee…

Computation and Language · Computer Science 2025-05-30 Xiaobao Wu , Liangming Pan , Yuxi Xie , Ruiwen Zhou , Shuai Zhao , Yubo Ma , Mingzhe Du , Rui Mao , Anh Tuan Luu , William Yang Wang

Large language models are increasingly trained on all the data ever produced by humans. Many have raised concerns about the trustworthiness of public benchmarks due to potential contamination in pre-training or fine-tuning datasets. While…

Computation and Language · Computer Science 2023-11-14 Shuo Yang , Wei-Lin Chiang , Lianmin Zheng , Joseph E. Gonzalez , Ion Stoica

Large volumes of text data have contributed significantly to the development of large language models (LLMs) in recent years. This data is typically acquired by scraping the internet, leading to pretraining datasets comprised of noisy web…

Computation and Language · Computer Science 2023-09-12 Max Marion , Ahmet Üstün , Luiza Pozzobon , Alex Wang , Marzieh Fadaee , Sara Hooker

We are currently in an era of fierce competition among various large language models (LLMs) continuously pushing the boundaries of benchmark performance. However, genuinely assessing the capabilities of these LLMs has become a challenging…

Computation and Language · Computer Science 2024-06-04 Wenhong Zhu , Hongkun Hao , Zhiwei He , Yunze Song , Yumeng Zhang , Hanxu Hu , Yiran Wei , Rui Wang , Hongyuan Lu

Data contamination in evaluation is getting increasingly prevalent with the emergence of language models pre-trained on super large, automatically crawled corpora. This problem leads to significant challenges in the accurate assessment of…

Computation and Language · Computer Science 2024-03-04 Yucheng Li , Frank Guerin , Chenghua Lin

In recent years, code intelligence has gained increasing importance in the field of automated software engineering. Meanwhile, the widespread adoption of Pretrained Language Models (PLMs) and Large Language Models (LLMs) has raised concerns…

Software Engineering · Computer Science 2026-02-09 Zhen Yang , Hongyi Lin , Yifan He , Junqi Wang , Zeyu Sun , Shuo Liu , Jie Xu , Pengpeng Wang , Zhongxing Yu , Qingyuan Liang

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…

Cryptography and Security · Computer Science 2025-07-16 Jérémie Dentan , Davide Buscaldi , Aymen Shabou , Sonia Vanier

Evaluating large language models (LLMs) is increasingly confounded by \emph{variant contamination}: the training corpus contains semantically equivalent yet lexically or syntactically altered versions of test items. Unlike verbatim leakage,…

Artificial Intelligence · Computer Science 2026-01-09 Renzhao Liang , Jingru Chen , Bo Jia , Bo Deng , Chenggang Xie , Yidong Wang , Ke Jin , Xin Wang , Linfeng Zhang , Cunxiang Wang

Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance.…

Computation and Language · Computer Science 2026-03-19 Yongding Tao , Tian Wang , Yihong Dong , Huanyu Liu , Kechi Zhang , Xiaolong Hu , Ge Li

In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation, ensuring that models forget not only specific training samples but also related implicit knowledge. To this end, we begin by…

Computation and Language · Computer Science 2025-10-10 Huazheng Wang , Yongcheng Jing , Haifeng Sun , Yingjie Wang , Jingyu Wang , Jianxin Liao , Dacheng Tao

Training data compositions for Large Language Models (LLMs) can significantly affect their downstream performance. However, a thorough data ablation study exploring large sets of candidate data mixtures is typically prohibitively expensive…

Computation and Language · Computer Science 2024-12-10 Clara Na , Ian Magnusson , Ananya Harsh Jha , Tom Sherborne , Emma Strubell , Jesse Dodge , Pradeep Dasigi

Large language models (LLMs) can be benchmark-contaminated, resulting in inflated scores that mask memorization as generalization, and in multilingual settings, this memorization can even transfer to "uncontaminated" languages. Using the…

Computation and Language · Computer Science 2026-01-29 David Tan , Pinzhen Chen , Josef van Genabith , Koel Dutta Chowdhury

Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques,…

Computation and Language · Computer Science 2024-06-07 Renren Jin , Jiangcun Du , Wuwei Huang , Wei Liu , Jian Luan , Bin Wang , Deyi Xiong

The development of large language models (LLMs) depends on trustworthy evaluation. However, most current evaluations rely on public benchmarks, which are prone to data contamination issues that significantly compromise fairness. Previous…

Computation and Language · Computer Science 2025-06-05 Kejian Zhu , Shangqing Tu , Zhuoran Jin , Lei Hou , Juanzi Li , Jun Zhao

Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks. Since LLMs train on wide swaths of the internet, this practice raises concerns of data…

Computation and Language · Computer Science 2023-10-17 Manley Roberts , Himanshu Thakur , Christine Herlihy , Colin White , Samuel Dooley

Benchmark datasets are critical for reproducible, reliable, and discriminative evaluation of LLMs. However, recent studies reveal that many benchmark datasets are included in pretraining corpora, i.e., $\textit{contaminated}$, which…

Machine Learning · Computer Science 2026-05-20 Ali Al-Lawati , Jason Lucas , Dongwon Lee , Suhang Wang