English
Related papers

Related papers: TaCo: Targeted Concept Erasure Prevents Non-Linear…

200 papers

Task arithmetic has emerged as a promising approach for editing models by representing task-specific knowledge as composable task vectors. However, existing methods rely on network linearization to derive task vectors, leading to…

Machine Learning · Computer Science 2025-04-04 Leonardo Iurada , Marco Ciccone , Tatiana Tommasi

Expressive neural text-to-speech (TTS) systems incorporate a style encoder to learn a latent embedding as the style information. However, this embedding process may encode redundant textual information. This phenomenon is called content…

Sound · Computer Science 2021-08-05 Xudong Dai , Cheng Gong , Longbiao Wang , Kaili Zhang

Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capabilities. This problem is further exacerbated by malicious…

Machine Learning · Computer Science 2026-05-22 Yifan Lan , Yuanpu Cao , Hanyu Wang , Lu Lin , Jinghui Chen

Explainability is a topic of growing importance in NLP. In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a layperson about a classifier's decision. We use this framework to…

Computation and Language · Computer Science 2020-10-13 Marcos V. Treviso , André F. T. Martins

Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mainly rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Mengyu Sun , Ziyuan Yang , Andrew Beng Jin Teoh , Junxu Liu , Haibo Hu , Yi Zhang

Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic representations. When these extracted concepts are used for downstream tasks such as…

Machine Learning · Computer Science 2026-04-29 Chandler Squires , Pradeep Ravikumar

While modern generative models such as diffusion-based architectures have enabled impressive creative capabilities, they also raise important safety and ethical risks. These concerns have led to growing interest in concept erasure, the…

Machine Learning · Computer Science 2026-04-14 Chi Zhang , Jingpu Cheng , Zhixian Wang , Ping Liu

Text-to-image person re-identification (TIReID) aims to retrieve person images from a large gallery given free-form textual descriptions. TIReID is challenging due to the substantial modality gap between visual appearances and textual…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Giyeol Kim , Chanho Eom

The heightened emphasis on the regulation of deep generative models, propelled by escalating concerns pertaining to privacy and compliance with regulatory frameworks, underscores the imperative need for precise control mechanisms over these…

Machine Learning · Computer Science 2024-06-21 Subhodip Panda , Prathosh AP

The growing concern over training data privacy has elevated the "Right to be Forgotten" into a critical requirement, thereby raising the demand for effective Machine Unlearning. However, existing unlearning approaches commonly suffer from a…

Machine Learning · Computer Science 2026-02-20 Haoyu Wang , Zhuo Huang , Xiaolong Wang , Bo Han , Zhiwei Lin , Tongliang Liu

Sparse linear models are one of several core tools for interpretable machine learning, a field of emerging importance as predictive models permeate decision-making in many domains. Unfortunately, sparse linear models are far less flexible…

Machine Learning · Statistics 2024-01-03 Ryan Thompson , Amir Dezfouli , Robert Kohn

Even when aggregate accuracy is high, state-of-the-art NLP models often fail systematically on specific subgroups of data, resulting in unfair outcomes and eroding user trust. Additional data collection may not help in addressing these…

Computation and Language · Computer Science 2023-05-30 Zexue He , Marco Tulio Ribeiro , Fereshte Khani

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Machine Learning · Computer Science 2026-05-19 Katarzyna Filus , Kamil Faber , Roberto Corizzo , Christopher Kanan

The rapid developments of various machine learning models and their deployments in several applications has led to discussions around the importance of looking beyond the accuracies of these models. Fairness of such models is one such…

Machine Learning · Computer Science 2024-04-16 Biswajit Rout , Ananya B. Sai , Arun Rajkumar

Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in…

Machine Learning · Computer Science 2023-02-07 Yuji Roh , Kangwook Lee , Steven Euijong Whang , Changho Suh

To mitigate the effects of undesired biases in models, several approaches propose to pre-process the input dataset to reduce the risks of discrimination by preventing the inference of sensitive attributes. Unfortunately, most of these…

Machine Learning · Computer Science 2023-02-21 Sébastien Gambs , Rosin Claude Ngueveu

With the increasing versatility of text-to-image diffusion models, the ability to selectively erase undesirable concepts (e.g., harmful content) has become indispensable. However, existing concept erasure approaches primarily focus on…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Yongwoo Kim , Sungmin Cha , Hyunsoo Kim , Jaewon Lee , Donghyun Kim

Despite the high accuracy offered by state-of-the-art deep natural-language models (e.g. LSTM, BERT), their application in real-life settings is still widely limited, as they behave like a black-box to the end-user. Hence, explainability is…

Computation and Language · Computer Science 2021-06-15 Francesco Ventura , Salvatore Greco , Daniele Apiletti , Tania Cerquitelli

Large-scale text-to-image diffusion models can generate high-fidelity images with powerful compositional ability. However, these models are typically trained on an enormous amount of Internet data, often containing copyrighted material,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Nupur Kumari , Bingliang Zhang , Sheng-Yu Wang , Eli Shechtman , Richard Zhang , Jun-Yan Zhu

Speech Entity Linking aims to recognize and disambiguate named entities in spoken languages. Conventional methods suffer gravely from the unfettered speech styles and the noisy transcripts generated by ASR systems. In this paper, we propose…

Computation and Language · Computer Science 2022-09-30 Shen Huang , Yuchen Zhai , Xinwei Long , Yong Jiang , Xiaobin Wang , Yin Zhang , Pengjun Xie