English
Related papers

Related papers: Estimating Contamination via Perplexity: Quantifyi…

200 papers

Large language models (LLMs) have demonstrated great performance across various benchmarks, showing potential as general-purpose task solvers. However, as LLMs are typically trained on vast amounts of data, a significant concern in their…

Computation and Language · Computer Science 2025-05-13 Yujuan Fu , Ozlem Uzuner , Meliha Yetisgen , Fei Xia

Dataset contamination, where evaluation datasets overlap with pre-training corpora, inflates performance metrics and undermines the reliability of model evaluations. Measuring dataset contamination thus becomes essential to ensure that…

Machine Learning · Computer Science 2025-05-22 Hyeong Kyu Choi , Maxim Khanov , Hongxin Wei , Yixuan Li

Large language models (LLMs) are commonly evaluated on challenging benchmarks such as AIME and Math500, where benchmark contamination can make memorized solutions appear as genuine reasoning. Existing detection methods largely rely on…

Computation and Language · Computer Science 2026-05-12 Zirui He , Haiyan Zhao , Yingcong Li , Ali Payani , Mengnan du

Benchmark-based evaluation is the de facto standard for comparing large language models (LLMs). However, its reliability is increasingly threatened by test set contamination, where test samples or their close variants leak into training…

Computation and Language · Computer Science 2026-01-28 Jianzhe Chai , Yu Zhe , Jun Sakuma

Data contamination has received increasing attention in the era of large language models (LLMs) due to their reliance on vast Internet-derived training corpora. To mitigate the risk of potential data contamination, LLM benchmarking has…

Machine Learning · Computer Science 2025-10-01 Simin Chen , Yiming Chen , Zexin Li , Yifan Jiang , Zhongwei Wan , Yixin He , Dezhi Ran , Tianle Gu , Haizhou Li , Tao Xie , Baishakhi Ray

Synthetic data has become essential for training foundation models, yet benchmark contamination threatens evaluation integrity. Although existing detection methods identify token-level overlap, they fail to detect semantic-level…

Machine Learning · Computer Science 2025-11-25 Sushant Mehta

Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data, which can compromise evaluation metrics, raise privacy concerns, and limit…

Machine Learning · Computer Science 2024-12-03 Eduardo Slonski

Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render benchmarks obsolete. To mitigate this, many recent benchmarks…

The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been…

Computation and Language · Computer Science 2024-02-26 Tianlin Li , Qian Liu , Tianyu Pang , Chao Du , Qing Guo , Yang Liu , Min Lin

Large Language Models (LLMs) are known to memorize portions of their training data, sometimes even reproduce content verbatim when prompted appropriately. Despite substantial interest, existing LLM memorization research has offered limited…

Computation and Language · Computer Science 2026-04-21 Yizhan Huang , Zhe Yang , Meifang Chen , Huang Nianchen , Jianping Zhang , Michael R. Lyu

Existing approaches for Large language model (LLM) detoxification generally rely on training on large-scale non-toxic or human-annotated preference data, designing prompts to instruct the LLM to generate safe content, or modifying the model…

Computation and Language · Computer Science 2025-06-03 Yuanhe Tian , Mingjie Deng , Guoqing Jin , Yan Song

Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appropriate underlying mechanisms and risking confirmation bias. We introduce a simple,…

Computation and Language · Computer Science 2026-04-01 Zoë Prins , Samuele Punzo , Frank Wildenburg , Giovanni Cinà , Sandro Pezzelle

The rapid advancement of large language models (LLMs) has heightened concerns about benchmark data contamination (BDC), where models inadvertently memorize evaluation data during the training process, inflating performance metrics, and…

Computation and Language · Computer Science 2025-09-23 Cheng Xu , Nan Yan , Shuhao Guan , Changhong Jin , Yuke Mei , Yibing Guo , M-Tahar Kechadi

In recent years, climate change repercussions have increasingly captured public interest. Consequently, corporations are emphasizing their environmental efforts in sustainability reports to bolster their public image. Yet, the absence of…

Computation and Language · Computer Science 2024-11-26 Avalon Vinella , Margaret Capetz , Rebecca Pattichis , Christina Chance , Reshmi Ghosh , Kai-Wei Chang

While pre-trained language models (LMs) have brought great improvements in many NLP tasks, there is increasing attention to explore capabilities of LMs and interpret their predictions. However, existing works usually focus only on a certain…

Computation and Language · Computer Science 2022-07-29 Yaozong Shen , Lijie Wang , Ying Chen , Xinyan Xiao , Jing Liu , Hua Wu

Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during…

Computation and Language · Computer Science 2024-10-23 Chonghua Liao , Ruobing Xie , Xingwu Sun , Haowen Sun , Zhanhui Kang

Public benchmarks increasingly govern how large language models (LLMs) are ranked, selected, and deployed. We frame this benchmark-centered regime as Silicon Bureaucracy and AI Test-Oriented Education, and argue that it rests on a fragile…

Artificial Intelligence · Computer Science 2026-03-31 Yiliang Song , Hongjun An , Jiangan Chen , Xuanchen Yan , Huan Song , Jiawei Shao , Xuelong Li

Recent advances in large language models (LLMs) have shown significant promise, yet their evaluation raises concerns, particularly regarding data contamination due to the lack of access to proprietary training data. To address this issue,…

Computation and Language · Computer Science 2025-05-30 Yanyang Li , Tin Long Wong , Cheung To Hung , Jianqiao Zhao , Duo Zheng , Ka Wai Liu , Michael R. Lyu , Liwei Wang

Concept bottleneck models (CBMs) ensure interpretability by decomposing predictions into human interpretable concepts. Yet the annotations used for training CBMs that enable this transparency are often noisy, and the impact of such…

Machine Learning · Computer Science 2026-02-02 Seonghwan Park , Jueun Mun , Donghyun Oh , Namhoon Lee

Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing…

Machine Learning · Computer Science 2023-03-07 Nicholas Carlini , Daphne Ippolito , Matthew Jagielski , Katherine Lee , Florian Tramer , Chiyuan Zhang