English
Related papers

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

200 papers

Data attribution methods quantify the influence of training data on model outputs and are becoming increasingly relevant for a wide range of LLM research and applications, including dataset curation, model interpretability, data valuation.…

Computation and Language · Computer Science 2025-10-28 Cathy Jiao , Yijun Pan , Emily Xiao , Daisy Sheng , Niket Jain , Hanzhang Zhao , Ishita Dasgupta , Jiaqi W. Ma , Chenyan Xiong

This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed the most to the…

Online reinforcement learning (RL) excels in complex, safety-critical domains but suffers from sample inefficiency, training instability, and limited interpretability. Data attribution provides a principled way to trace model behavior back…

Machine Learning · Computer Science 2025-10-07 Yuzheng Hu , Fan Wu , Haotian Ye , David Forsyth , James Zou , Nan Jiang , Jiaqi W. Ma , Han Zhao

Training data attribution (TDA) methods ask which training documents are responsible for a model behavior. However, models often learn broad concepts shared across many examples. Moreover, existing TDA methods are supervised -- they require…

Artificial Intelligence · Computer Science 2026-03-18 J Rosser

Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. Many efforts have been made to address the mismatch between the distributions of training and…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Pingyang Dai , Peixian Chen , Qiong Wu , Xiaopeng Hong , Qixiang Ye , Qi Tian , Rongrong Ji

The existing supervised relation extraction methods have achieved impressive performance in a closed-set setting, where the relations during both training and testing remain the same. In a more realistic open-set setting, unknown relations…

Computation and Language · Computer Science 2023-06-09 Jun Zhao , Xin Zhao , Wenyu Zhan , Qi Zhang , Tao Gui , Zhongyu Wei , Yunwen Chen , Xiang Gao , Xuanjing Huang

Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigating…

Unsupervised domain adaptation (UDA) is a statistical learning problem when the distribution of training (source) data is different from that of test (target) data. In this setting, one has access to labeled data only from the source domain…

Machine Learning · Computer Science 2026-02-24 Seonghwi Kim , Sung Ho Jo , Wooseok Ha , Minwoo Chae

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance…

Machine Learning · Computer Science 2025-02-18 Ahmad Chaddad , Yihang Wu , Yuchen Jiang , Ahmed Bouridane , Christian Desrosiers

Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. In this work, we address the problem of…

Computation and Language · Computer Science 2026-01-08 Ruihan Zhang , Jun Sun

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Machine Learning · Computer Science 2025-05-13 Zhiqiang Wang , Ruoxi Cheng

This paper proposes deception as a mechanism for out-of-distribution (OOD) generalization: by learning data representations that make training data appear independent and identically distributed (iid) to an observer, we can identify stable…

Machine Learning · Computer Science 2025-09-16 Anirudha Majumdar

Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…

Computer Vision and Pattern Recognition · Computer Science 2019-05-14 Songsong Wu , Yan Yan , Hao Tang , Jianjun Qian , Jian Zhang , Xiao-Yuan Jing

The utility of large language models (LLMs) depends heavily on the quality and quantity of their training data. Many organizations possess large data corpora that could be leveraged to train or fine-tune LLMs tailored to their specific…

Machine Learning · Computer Science 2025-02-11 Tom Segal , Asaf Shabtai , Yuval Elovici

As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by…

Training Data Attribution (TDA) seeks to trace model predictions back to influential training examples, enhancing interpretability and safety. We formulate TDA as a Bayesian information-theoretic problem: subsets are scored by the…

Machine Learning · Computer Science 2026-04-10 Dharmesh Tailor , Nicolò Felicioni , Kamil Ciosek

We study a robust alternative to empirical risk minimization called distributionally robust learning (DRL), in which one learns to perform against an adversary who can choose the data distribution from a specified set of distributions. We…

Machine Learning · Computer Science 2019-12-19 Charlie Frogner , Sebastian Claici , Edward Chien , Justin Solomon

Large Language Models (LLMs) utilize large amounts of data for their training, some of which may come from copyrighted sources. Membership Inference Attacks (MIA) aim to detect those documents and whether they have been included in the…

Artificial Intelligence · Computer Science 2026-04-22 Juliusz Janicki , Savvas Chamezopoulos , Evangelos Kanoulas , Georgios Tsatsaronis

The emergence of text-to-image models has recently sparked significant interest, but the attendant is a looming shadow of potential infringement by violating the user terms. Specifically, an adversary may exploit data created by a…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Likun Zhang , Hao Wu , Lingcui Zhang , Fengyuan Xu , Jin Cao , Fenghua Li , Ben Niu

Data Attribution (DA) is an emerging approach in the field of eXplainable Artificial Intelligence (XAI), aiming to identify influential training datapoints which determine model outputs. It seeks to provide transparency about the model and…

Machine Learning · Computer Science 2025-12-22 Galip Ümit Yolcu , Moritz Weckbecker , Thomas Wiegand , Wojciech Samek , Sebastian Lapuschkin