English
Related papers

Related papers: Detecting and Filtering Unsafe Training Data via D…

200 papers

Training data detection is critical for enforcing copyright and data licensing, as Large Language Models (LLM) are trained on massive text corpora scraped from the internet. We present SPECTRA, a watermarking approach that makes training…

Computation and Language · Computer Science 2026-03-25 Pranav Shetty , Mirazul Haque , Petr Babkin , Zhiqiang Ma , Xiaomo Liu , Manuela Veloso

Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Ji Zhang , Lianli Gao , Xu Luo , Hengtao Shen , Jingkuan Song

This thesis makes considerable contributions to the realm of machine learning, specifically in the context of open-world scenarios where systems face previously unseen data and contexts. Traditional machine learning models are usually…

Machine Learning · Computer Science 2023-10-11 Yiyou Sun

Protecting personal data against exploitation of machine learning models is crucial. Recently, availability attacks have shown great promise to provide an extra layer of protection against the unauthorized use of data to train neural…

Machine Learning · Computer Science 2024-01-12 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

Large language models (LLMs) have demonstrated exceptional performance across a wide range of tasks and domains, with data preparation playing a critical role in achieving these results. Pre-training data typically combines information from…

Computation and Language · Computer Science 2024-09-27 Hao Liang , Keshi Zhao , Yajie Yang , Bin Cui , Guosheng Dong , Zenan Zhou , Wentao Zhang

Imitating skills from low-quality datasets, such as sub-optimal demonstrations and observations with distractors, is common in real-world applications. In this work, we focus on the problem of Learning from Noisy Demonstrations (LND), where…

Machine Learning · Computer Science 2024-04-05 Kaichen Huang , Hai-Hang Sun , Shenghua Wan , Minghao Shao , Shuai Feng , Le Gan , De-Chuan Zhan

Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…

Machine Learning · Computer Science 2025-10-23 Xiaoyu Wu , Yifei Pang , Terrance Liu , Zhiwei Steven Wu

Training data attribution (TDA) identifies which training examples most influenced a model's prediction. Influence function methods are a theoretically grounded family of TDA methods and exploit gradients. To overcome the scalability…

Machine Learning · Computer Science 2026-05-15 Shuangqi Li , Hieu Le , Jingyi Xu , Mathieu Salzmann

Large Reasoning Models (LRMs) have advanced automated multi-step reasoning, but their ability to generate complex Chain-of-Thought (CoT) trajectories introduces severe privacy risks, as sensitive information may be deeply embedded…

Artificial Intelligence · Computer Science 2026-01-15 Jingjing Zhou , Gaoxiang Cong , Li Su , Liang Li

Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current TDA approaches lack reliability and robustness, preventing their adoption in real-world…

Machine Learning · Computer Science 2026-05-19 Joan Serrà , Dipam Goswami , Fabio Morreale , Wei-Hsiang Liao , Yuki Mitsufuji

Semi-supervised domain adaptation (SSDA) aims to adapt models trained from a labeled source domain to a different but related target domain, from which unlabeled data and a small set of labeled data are provided. Current methods that treat…

Computer Vision and Pattern Recognition · Computer Science 2021-09-24 Luyu Yang , Yan Wang , Mingfei Gao , Abhinav Shrivastava , Kilian Q. Weinberger , Wei-Lun Chao , Ser-Nam Lim

Training data attribution (TDA) techniques find influential training data for the model's prediction on the test data of interest. They approximate the impact of down- or up-weighting a particular training sample. While conceptually useful,…

Machine Learning · Computer Science 2023-11-01 Elisa Nguyen , Minjoon Seo , Seong Joon Oh

We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect such domain shifts via a differentiable density ratio…

Machine Learning · Computer Science 2024-02-07 Haoxuan Wang , Zhiding Yu , Yisong Yue , Anima Anandkumar , Anqi Liu , Junchi Yan

Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric applications in modern AI. Despite a recent surge of new methods…

Machine Learning · Computer Science 2025-10-24 Weiyi Wang , Junwei Deng , Yuzheng Hu , Shiyuan Zhang , Xirui Jiang , Runting Zhang , Han Zhao , Jiaqi W. Ma

Unlearning in large language models is becoming increasingly important due to regulatory compliance, copyright protection, and privacy concerns. However, a key challenge in LLM unlearning is unintended forgetting, where the removal of…

Machine Learning · Computer Science 2025-10-23 Peizhi Niu , Evelyn Ma , Huiting Zhou , Duo Zhou , Huan Zhang , S. Rasoul Etesami , Olgica Milenkovic

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Computation and Language · Computer Science 2023-11-30 Jiaxin Wen , Pei Ke , Hao Sun , Zhexin Zhang , Chengfei Li , Jinfeng Bai , Minlie Huang

Data attribution seeks to trace model outputs back to training data. With the recent development of diffusion models, data attribution has become a desired module to properly assign valuations for high-quality or copyrighted training…

Machine Learning · Computer Science 2024-03-18 Xiaosen Zheng , Tianyu Pang , Chao Du , Jing Jiang , Min Lin

Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Ashish Seth , Mayur Hemani , Chirag Agarwal

Distribution shift is a major obstacle in offline reinforcement learning, which necessitates minimizing the discrepancy between the learned policy and the behavior policy to avoid overestimating rare or unseen actions. Previous conservative…

Machine Learning · Computer Science 2024-06-12 Zeyuan Liu , Kai Yang , Xiu Li

Domain adaptation (DA) aims to enable a learning model trained from a source domain to generalize well on a target domain, despite the mismatch of data distributions between the two domains. State-of-the-art DA methods have so far focused…

Computer Vision and Pattern Recognition · Computer Science 2021-01-13 Lingkun Luo , Liming Chen , Shiqiang Hu