English
Related papers

Related papers: No Training Wheels: Steering Vectors for Bias Corr…

200 papers

Neural network architectures have been extensively employed in the fair representation learning setting, where the objective is to learn a new representation for a given vector which is independent of sensitive information. Various…

Machine Learning · Computer Science 2022-02-08 Mattia Cerrato , Alesia Vallenas Coronel , Marius Köppel , Alexander Segner , Roberto Esposito , Stefan Kramer

Bias mitigation in machine learning models is imperative, yet challenging. While several approaches have been proposed, one view towards mitigating bias is through adversarial learning. A discriminator is used to identify the bias…

Machine Learning · Computer Science 2022-02-23 Vinod K Kurmi , Rishabh Sharma , Yash Vardhan Sharma , Vinay P. Namboodiri

We train a network to generate mappings between training sets and classification policies (a 'classifier generator') by conditioning on the entire training set via an attentional mechanism. The network is directly optimized for test set…

Machine Learning · Computer Science 2018-04-02 Nicholas Guttenberg , Ryota Kanai

Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine…

Machine Learning · Computer Science 2020-07-01 Kristy Choi , Aditya Grover , Trisha Singh , Rui Shu , Stefano Ermon

Mitigating bias in language models (LMs) has become a critical problem due to the widespread deployment of LMs. Numerous approaches revolve around data pre-processing and fine-tuning of language models, tasks that can be both time-consuming…

Computation and Language · Computer Science 2024-06-21 Omkar Dige , Diljot Singh , Tsz Fung Yau , Qixuan Zhang , Borna Bolandraftar , Xiaodan Zhu , Faiza Khan Khattak

Semi-supervised learning plays an important role in large-scale machine learning. Properly using additional unlabeled data (largely available nowadays) often can improve the machine learning accuracy. However, if the machine learning model…

Machine Learning · Computer Science 2017-05-02 Zhaocai Sun , William K. Cheung , Xiaofeng Zhang , Jun Yang

In the absence of large labelled datasets, self-supervised learning techniques can boost performance by learning useful representations from unlabelled data, which is often more readily available. However, there is often a domain shift…

Machine Learning · Computer Science 2020-06-23 Linus Ericsson , Henry Gouk , Timothy M. Hospedales

Image classifiers play a critical role in detecting diseases in medical imaging and identifying anomalies in manufacturing processes. However, their predefined behaviors after extensive training make post hoc model editing difficult,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Jaeik Kim , Jaeyoung Do

Just like weights, bias terms are the learnable parameters of many popular machine learning models, including neural networks. Biases are thought to enhance the representational power of neural networks, enabling them to solve a variety of…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Chuqin Geng , Xiaojie Xu , Haolin Ye , Xujie Si

Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effective than optimization-free ones. However, current…

Machine Learning · Computer Science 2026-05-08 Yuntai Bao , Qinfeng Li , Xinyan Yu , Xuhong Zhang , Ge Su , Wenqi Zhang , Liu Yan , Haiqin Weng , Jianwei Yin

Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has begun to characterize this phenomenon but leaves open…

Computation and Language · Computer Science 2026-04-29 George Morgulis , John Hewitt

Applications based on Machine Learning models have now become an indispensable part of the everyday life and the professional world. A critical question then recently arised among the population: Do algorithmic decisions convey any type of…

Machine Learning · Statistics 2020-04-07 Philippe Besse , Eustasio del Barrio , Paula Gordaliza , Jean-Michel Loubes , Laurent Risser

Borrowing from the transformer models that revolutionized the field of natural language processing, self-supervised feature learning for visual tasks has also seen state-of-the-art success using these extremely deep, isotropic networks.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-01 George Cazenavette , Simon Lucey

The measurement of bias in machine learning often focuses on model performance across identity subgroups (such as man and woman) with respect to groundtruth labels. However, these methods do not directly measure the associations that a…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Osman Aka , Ken Burke , Alex Bäuerle , Christina Greer , Margaret Mitchell

Steering language models (LMs) by modifying internal activations is a popular approach for controlling text generation. Unsupervised dictionary learning methods, e.g., sparse autoencoders, can be scaled to produce many steering vectors, but…

Computation and Language · Computer Science 2025-06-05 Jiuding Sun , Sidharth Baskaran , Zhengxuan Wu , Michael Sklar , Christopher Potts , Atticus Geiger

Evaluation of treatment effects and more general estimands is typically achieved via parametric modelling, which is unsatisfactory since model misspecification is likely. Data-adaptive model building (e.g. statistical/machine learning) is…

Statistics Theory · Mathematics 2022-01-14 Oliver Hines , Oliver Dukes , Karla Diaz-Ordaz , Stijn Vansteelandt

In many applied fields incomplete covariate vectors are commonly encountered. It is well known that this can be problematic when making inference on model parameters, but its impact on prediction performance is less understood. We develop a…

Methodology · Statistics 2020-07-14 Garritt L. Page , Fernando A. Quintana , Peter Müller

Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Javier Ferrando , Enrique Lopez-Cuena , Pablo Agustin Martin-Torres , Daniel Hinjos , Anna Arias-Duart , Dario Garcia-Gasulla

Class-level machine unlearning aims to remove the influence of specified classes while preserving model utility on retained classes. Existing methods are commonly evaluated by retain-set accuracy, forget-set accuracy, and unlearning time,…

Machine Learning · Computer Science 2026-05-12 Weidong Zheng , Kongyang Chen , Yuanwei Guo , Yatie Xiao

Models trained on real-world data tend to imitate and amplify social biases. Common methods to mitigate biases require prior information on the types of biases that should be mitigated (e.g., gender or racial bias) and the social groups…

Computation and Language · Computer Science 2023-06-13 Hadas Orgad , Yonatan Belinkov