中文
相关论文

相关论文: Automated Detection of Pre-training Text in Black-…

200 篇论文

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…

计算与语言 · 计算机科学 2024-06-04 Zhenhua Liu , Tong Zhu , Chuanyuan Tan , Haonan Lu , Bing Liu , Wenliang Chen

Large vision-language models (LVLMs) derive their capabilities from extensive training on vast corpora of visual and textual data. Empowered by large-scale parameters, these models often exhibit strong memorization of their training data,…

密码学与安全 · 计算机科学 2025-11-05 Jinhua Yin , Peiru Yang , Chen Yang , Huili Wang , Zhiyang Hu , Shangguang Wang , Yongfeng Huang , Tao Qi

While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current…

计算与语言 · 计算机科学 2024-08-01 Anqi Zhang , Chaofeng Wu

Although large language models (LLMs) are widely deployed, the data used to train them is rarely disclosed. Given the incredible scale of this data, up to trillions of tokens, it is all but certain that it includes potentially problematic…

计算与语言 · 计算机科学 2024-03-12 Weijia Shi , Anirudh Ajith , Mengzhou Xia , Yangsibo Huang , Daogao Liu , Terra Blevins , Danqi Chen , Luke Zettlemoyer

Pre-trained Language Models (PLMs) are trained on large amounts of unlabeled data, yet they exhibit remarkable reasoning skills. However, the trustworthiness challenges posed by these black-box models have become increasingly evident in…

计算与语言 · 计算机科学 2025-08-26 Yunxiao Zhao , Hao Xu , Zhiqiang Wang , Xiaoli Li , Jiye Liang , Ru Li

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

密码学与安全 · 计算机科学 2024-12-03 Erick Galinkin , Martin Sablotny

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…

计算与语言 · 计算机科学 2025-06-23 Nicolas Yax , Pierre-Yves Oudeyer , Stefano Palminteri

A wide variety of natural language tasks are currently being addressed with large-scale language models (LLMs). These models are usually trained with a very large amount of unsupervised text data and adapted to perform a downstream natural…

计算与语言 · 计算机科学 2023-10-09 Lautaro Estienne , Luciana Ferrer , Matías Vera , Pablo Piantanida

Training data is a critical and often proprietary asset in Large Language Model (LLM) development, motivating the use of data watermarking to embed model-transferable signals for usage verification. We identify low coverage as a vital yet…

密码学与安全 · 计算机科学 2026-04-30 Hengyu Wu , Yang Cao

Despite being prevalent in the general field of Natural Language Processing (NLP), pre-trained language models inherently carry privacy and copyright concerns due to their nature of training on large-scale web-scraped data. In this paper,…

计算与语言 · 计算机科学 2024-08-21 Yuan Xin , Zheng Li , Ning Yu , Dingfan Chen , Mario Fritz , Michael Backes , Yang Zhang

As large language models (LLMs) are trained on increasingly vast and opaque text corpora, determining which data contributed to training has become essential for copyright enforcement, compliance auditing, and user trust. While prior work…

计算与语言 · 计算机科学 2026-03-30 Pranav Shetty , Mirazul Haque , Zhiqiang Ma , Xiaomo Liu

Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and are increasingly integrated into the software development process. However, ensuring the correctness of LLM-generated code remains a critical…

软件工程 · 计算机科学 2025-10-06 Thanh Trong Vu , Tuan-Dung Bui , Thu-Trang Nguyen , Son Nguyen , Hieu Dinh Vo

As the scale of training corpora for large language models (LLMs) grows, model developers become increasingly reluctant to disclose details on their data. This lack of transparency poses challenges to scientific evaluation and ethical…

计算与语言 · 计算机科学 2025-05-22 Weichao Zhang , Ruqing Zhang , Jiafeng Guo , Maarten de Rijke , Yixing Fan , Xueqi Cheng

Large language models (LLMs) have demonstrated remarkable capabilities in generating high-quality texts across diverse domains. However, the potential misuse of LLMs has raised significant concerns, underscoring the urgent need for reliable…

计算与语言 · 计算机科学 2024-10-10 Yihuai Xu , Yongwei Wang , Yifei Bi , Huangsen Cao , Zhouhan Lin , Yu Zhao , Fei Wu

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing…

计算机视觉与模式识别 · 计算机科学 2024-12-20 Qirui Jiao , Daoyuan Chen , Yilun Huang , Yaliang Li , Ying Shen

This paper introduces ThoughtProbe, a novel inference time framework that leverages the hidden reasoning features of Large Language Models (LLMs) to improve their reasoning performance. Unlike previous works that manipulate the hidden…

计算与语言 · 计算机科学 2025-11-03 Zijian Wang , Chang Xu

The increasing parameters and expansive dataset of large language models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have…

计算与语言 · 计算机科学 2024-12-30 Wenjie Fu , Huandong Wang , Chen Gao , Guanghua Liu , Yong Li , Tao Jiang

Large Language Models (LLMs) utilize extensive knowledge databases and show powerful text generation ability. However, their reliance on high-quality copyrighted datasets raises concerns about copyright infringements in generated texts.…

计算与语言 · 计算机科学 2026-01-05 Qichao Ma , Rui-Jie Zhu , Peiye Liu , Renye Yan , Fahong Zhang , Ling Liang , Meng Li , Zhaofei Yu , Zongwei Wang , Yimao Cai , Tiejun Huang

Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as…

密码学与安全 · 计算机科学 2024-10-01 Zeguan Xiao , Yan Yang , Guanhua Chen , Yun Chen

This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a…

计算与语言 · 计算机科学 2024-02-08 Yutian Chen , Hao Kang , Vivian Zhai , Liangze Li , Rita Singh , Bhiksha Raj
‹ 上一页 1 2 3 10 下一页 ›