English
Related papers

Related papers: Estimating Contamination via Perplexity: Quantifyi…

200 papers

Large language models (LLMs) are widely used, but concerns about data contamination challenge the reliability of LLM evaluations. Existing contamination detection methods are often task-specific or require extra prerequisites, limiting…

Computation and Language · Computer Science 2024-10-22 Yi Zhao , Jing Li , Linyi Yang

Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance. A central challenge in assessing this risk is distinguishing genuine memorization of training data from…

Machine Learning · Computer Science 2026-02-24 Trishita Tiwari , Ari Trachtenberg , G. Edward Suh

Various techniques have been proposed to leverage the capabilities of code language models (CLMs) for SE tasks. While these techniques typically evaluate their effectiveness using publicly available datasets, the evaluation can be subject…

Software Engineering · Computer Science 2024-03-29 Jialun Cao , Wuqi Zhang , Shing-Chi Cheung

Large Language Models (LLMs) have revolutionized code generation, achieving exceptional results on various established benchmarking frameworks. However, concerns about data contamination - where benchmark data inadvertently leaks into…

Hardware Architecture · Computer Science 2025-06-13 Zeng Wang , Minghao Shao , Jitendra Bhandari , Likhitha Mankali , Ramesh Karri , Ozgur Sinanoglu , Muhammad Shafique , Johann Knechtel

Pre-trained neural language models give high performance on natural language inference (NLI) tasks. But whether they actually understand the meaning of the processed sequences remains unclear. We propose a new diagnostics test suite which…

Computation and Language · Computer Science 2021-04-13 Aarne Talman , Marianna Apidianaki , Stergios Chatzikyriakidis , Jörg Tiedemann

Evidence-enhanced detectors present remarkable abilities in identifying malicious social text. However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors. This paper explores…

Computation and Language · Computer Science 2025-05-30 Herun Wan , Minnan Luo , Zhixiong Su , Guang Dai , Xiang Zhao

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…

Cryptography and Security · Computer Science 2025-06-09 Tingchen Fu , Mrinank Sharma , Philip Torr , Shay B. Cohen , David Krueger , Fazl Barez

We show that a language model's ability to predict text is tightly linked to the breadth of its embedding space: models that spread their contextual representations more widely tend to achieve lower perplexity. Concretely, we find that…

Computation and Language · Computer Science 2026-04-21 Yanhong Li , Ming Li , Karen Livescu , Jiawei Zhou

Language models can be prompted to perform a wide variety of zero- and few-shot learning problems. However, performance varies significantly with the choice of prompt, and we do not yet understand why this happens or how to pick the best…

Computation and Language · Computer Science 2024-09-16 Hila Gonen , Srini Iyer , Terra Blevins , Noah A. Smith , Luke Zettlemoyer

Benchmark-based evaluation, e.g., multiple-choice questions (MCQs) and open-ended questions (OEQs), is widely used for evaluating Large Language Models (LLMs), yet their reliability is undermined by benchmark contamination. When pre-exposed…

Computation and Language · Computer Science 2026-05-18 Yuyang Xu , Renjun Hu , Haochao Ying , Jian Wu , Xing Shi , Wei Lin

Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…

Computation and Language · Computer Science 2022-03-08 Canwen Xu , Zexue He , Zhankui He , Julian McAuley

Content moderation typically combines the efforts of human moderators and machine learning models. However, these systems often rely on data where significant disagreement occurs during moderation, reflecting the subjective nature of…

Computation and Language · Computer Science 2025-09-01 Guillermo Villate-Castillo , Javier Del Ser , Borja Sanz

State-of-the-art pre-trained language models have been shown to memorise facts and perform well with limited amounts of training data. To gain a better understanding of how these models learn, we study their generalisation and memorisation…

Computation and Language · Computer Science 2022-03-16 Michael Tänzer , Sebastian Ruder , Marek Rei

Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs' training data, it could…

Computation and Language · Computer Science 2024-06-03 Yihong Dong , Xue Jiang , Huanyu Liu , Zhi Jin , Bin Gu , Mengfei Yang , Ge Li

We develop a methodology for analyzing language model task performance at the individual example level based on training data density estimation. Experiments with paraphrasing as a controlled intervention on finetuning data demonstrate that…

The rapid development of large language models (LLMs) has transformed the landscape of natural language processing. Evaluating LLMs properly is crucial for understanding their potential and addressing concerns such as safety. However, LLM…

Computation and Language · Computer Science 2025-05-14 Rahmatullah Musawi , Sheng Lu

Large Language Models have demonstrated remarkable capabilities in natural language processing, yet their decision-making processes often lack transparency. This opaqueness raises significant concerns regarding trust, bias, and model…

This study addresses the reliability of automatic summarization in high-risk scenarios and proposes a large language model framework that integrates uncertainty quantification and risk-aware mechanisms. Starting from the demands of…

Computation and Language · Computer Science 2025-10-03 Shuaidong Pan , Di Wu

If LLM training data is polluted with benchmark test data, then benchmark performance gives biased estimates of out-of-distribution (OOD) generalization. Typical decontamination filters use n-gram matching which fail to detect semantic…

Machine Learning · Computer Science 2026-02-16 Ari Spiesberger , Juan J. Vazquez , Nicky Pochinkov , Tomáš Gavenčiak , Peli Grietzer , Gavin Leech , Nandi Schoots

Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is…

Computation and Language · Computer Science 2024-06-04 Zhenhua Liu , Tong Zhu , Chuanyuan Tan , Haonan Lu , Bing Liu , Wenliang Chen
‹ Prev 1 4 5 6 7 8 10 Next ›