English
Related papers

Related papers: Quanda: An Interpretability Toolkit for Training D…

200 papers

QuaPy is an open-source framework for performing quantification (a.k.a. supervised prevalence estimation), written in Python. Quantification is the task of training quantifiers via supervised learning, where a quantifier is a predictor that…

Machine Learning · Computer Science 2021-06-22 Alejandro Moreo , Andrea Esuli , Fabrizio Sebastiani

Many training data attribution (TDA) methods aim to estimate how a model's behavior would change if one or more data points were removed from the training set. Methods based on implicit differentiation, such as influence functions, can be…

Machine Learning · Computer Science 2024-05-22 Juhan Bae , Wu Lin , Jonathan Lorraine , Roger Grosse

Training data attribution (TDA) methods aim to quantify the influence of individual training data points on the model predictions, with broad applications in data-centric AI, such as mislabel detection, data selection, and copyright…

Machine Learning · Computer Science 2024-05-28 Junwei Deng , Ting-Wei Li , Shichang Zhang , Jiaqi Ma

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Aziz Bacha , Thomas George

Machine learning has recently been widely adopted to address the managerial decision making problems, in which the decision maker needs to be able to interpret the contributions of individual attributes in an explicit form. However, there…

Machine Learning · Computer Science 2019-10-28 Mengzhuo Guo , Qingpeng Zhang , Xiuwu Liao , Frank Youhua Chen , Daniel Dajun Zeng

We propose TANDA, an effective technique for fine-tuning pre-trained Transformer models for natural language tasks. Specifically, we first transfer a pre-trained model into a model for a general task by fine-tuning it with a large and…

Computation and Language · Computer Science 2019-11-21 Siddhant Garg , Thuy Vu , Alessandro Moschitti

Missing values are a major challenge in most data science projects working on real data. To avoid losing valuable information, imputation methods are used to fill in missing values with estimates, allowing the preservation of samples or…

Machine Learning · Computer Science 2024-07-17 Pedro Pons-Suñer , Laura Arnal , J. Ramón Navarro-Cerdán , François Signol

Explainable Artificial Intelligence (XAI) methods are increasingly used in safety-critical domains, yet there is no unified framework to jointly evaluate fidelity, interpretability, robustness, fairness, and completeness. We address this…

Artificial Intelligence · Computer Science 2026-04-10 Md. Ariful Islam , Md Abrar Jahin , M. F. Mridha , Nilanjan Dey

Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest. Numerous tricks and techniques have been proposed to ensure robust learning on arbitrary streams of unlabeled data.…

Machine Learning · Computer Science 2023-11-13 Saypraseuth Mounsaveng , Florent Chiaroni , Malik Boudiaf , Marco Pedersoli , Ismail Ben Ayed

The increasing complexity of AI systems has made understanding their behavior critical. Numerous interpretability methods have been developed to attribute model behavior to three key aspects: input features, training data, and internal…

Machine Learning · Computer Science 2025-05-30 Shichang Zhang , Tessa Han , Usha Bhalla , Himabindu Lakkaraju

Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for. They ignore the fact that, due to stochasticity in the initialisation…

Machine Learning · Computer Science 2025-10-28 Bruno Mlodozeniec , Isaac Reid , Sam Power , David Krueger , Murat Erdogdu , Richard E. Turner , Roger Grosse

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

Machine Learning · Computer Science 2019-11-06 Mengjiao Yang , Been Kim

Test-time adaptation (TTA) aims to transfer knowledge from a source model to unknown test data with potential distribution shifts in an online manner. Many existing TTA methods rely on entropy as a confidence metric to optimize the model.…

Machine Learning · Computer Science 2025-10-07 Chang'an Yi , Xiaohui Deng , Shuaicheng Niu , Yan Zhou

Training data attribution (TDA) methods aim to attribute model outputs back to specific training examples, and the application of these methods to large language model (LLM) outputs could significantly advance model transparency and data…

Computation and Language · Computer Science 2024-12-24 Tyler A. Chang , Dheeraj Rajagopal , Tolga Bolukbasi , Lucas Dixon , Ian Tenney

Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift. While many methods have been proposed in the literature,…

Attribution methods seek to explain language model predictions by quantifying the contribution of input tokens to generated outputs. However, most existing techniques are designed for encoder-based architectures and rely on linear…

Computation and Language · Computer Science 2026-04-16 Vishal Pramanik , Maisha Maliha , Nathaniel D. Bastian , Sumit Kumar Jha

Training data attribution (TDA) for music generation must answer two questions that copyright analysis requires, namely which training songs influence a generated output and along which musical aspects the influence operates. Existing…

Sound · Computer Science 2026-05-18 Changheon Han , Ashkan Panahi , Kıvanç Tatar

The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) methods are considered…

Computation and Language · Computer Science 2024-11-20 Kangxi Wu , Liang Pang , Huawei Shen , Xueqi Cheng

Test-Time Adaptation (TTA) has recently emerged as a promising approach for tackling the robustness challenge under distribution shifts. However, the lack of consistent settings and systematic studies in prior literature hinders thorough…

Machine Learning · Computer Science 2023-06-07 Hao Zhao , Yuejiang Liu , Alexandre Alahi , Tao Lin

Test-time adaptation (TTA) aims to adapt a model, initially trained on training data, to test data with potential distribution shifts. Most existing TTA methods focus on classification problems. The pronounced success of classification…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Chang'an Yi , Haotian Chen , Yifan Zhang , Yonghui Xu , Yan Zhou , Lizhen Cui