English
Related papers

Related papers: Erasing Conceptual Knowledge from Language Models

200 papers

Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically…

Machine Learning · Computer Science 2025-06-03 Zhili Feng , Yixuan Even Xu , Alexander Robey , Robert Kirk , Xander Davies , Yarin Gal , Avi Schwarzschild , J. Zico Kolter

Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches…

Artificial Intelligence · Computer Science 2026-03-20 Duc Hao Pham , Van Duy Truong , Duy Khanh Dinh , Tien Cuong Nguyen , Dien Hy Ngo , Tuan Anh Bui

Concept erasure techniques have recently gained significant attention for their potential to remove unwanted concepts from text-to-image models. While these methods often demonstrate promising results in controlled settings, their…

Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic…

Computation and Language · Computer Science 2025-05-29 Haoming Xu , Ningyuan Zhao , Liming Yang , Sendong Zhao , Shumin Deng , Mengru Wang , Bryan Hooi , Nay Oo , Huajun Chen , Ningyu Zhang

As large pre-trained language models become increasingly critical to natural language understanding (NLU) tasks, their substantial computational and memory requirements have raised significant economic and environmental concerns. Addressing…

Computation and Language · Computer Science 2025-11-03 Shang Wang

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ensuring alignment and thus safe use. However, accurately and…

Computation and Language · Computer Science 2024-11-01 Chris Yuhao Liu , Yaxuan Wang , Jeffrey Flanigan , Yang Liu

Large language models (LLMs) encode vast amounts of world knowledge. However, since these models are trained on large swaths of internet data, they are at risk of inordinately capturing information about dominant groups. This imbalance can…

Computation and Language · Computer Science 2023-10-24 Pola Schwöbel , Jacek Golebiowski , Michele Donini , Cédric Archambeau , Danish Pruthi

In recent years, large language models (LLMs) have spurred a new research paradigm in natural language processing. Despite their excellent capability in knowledge-based question answering and reasoning, their potential to retain faulty or…

Computation and Language · Computer Science 2023-12-11 Nianwen Si , Hao Zhang , Heyu Chang , Wenlin Zhang , Dan Qu , Weiqiang Zhang

Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove specific content…

Computation and Language · Computer Science 2025-08-12 Xiaojian Yuan , Tianyu Pang , Chao Du , Kejiang Chen , Weiming Zhang , Min Lin

As the Large Language Model (LLM) gains widespread adoption, increasing attention has been given to the challenge of making LLM forget non-compliant data memorized during its pre-training. Machine Unlearning focuses on efficiently erasing…

Computation and Language · Computer Science 2025-08-19 Yujian Sun , Tian Li

Text embeddings have become an essential part of a variety of language applications. However, methods for interpreting, exploring and reversing embedding spaces are limited, reducing transparency and precluding potentially valuable…

Computation and Language · Computer Science 2026-01-27 Brian Ondov , Chia-Hsuan Chang , Yujia Zhou , Mauro Giuffrè , Hua Xu

Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during pretraining. This paper addresses the challenge of modifying…

Computation and Language · Computer Science 2024-09-23 Akshaj Kumar Veldanda , Shi-Xiong Zhang , Anirban Das , Supriyo Chakraborty , Stephen Rawls , Sambit Sahu , Milind Naphade

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…

Computation and Language · Computer Science 2025-09-30 Qingjie Zhang , Haoting Qian , Zhicong Huang , Cheng Hong , Minlie Huang , Ke Xu , Chao Zhang , Han Qiu

Large Language Models (LLMs) have shown strong potential in accelerating digital hardware design through automated code generation. Yet, ensuring their reliability remains a critical challenge, as existing LLMs trained on massive…

Machine Learning · Computer Science 2025-12-08 Yiwen Liang , Qiufeng Li , Shikai Wang , Weidong Cao

Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning involves balancing between forget quality (effectively…

Machine Learning · Computer Science 2025-06-23 Shengyuan Hu , Neil Kale , Pratiksha Thaker , Yiwei Fu , Steven Wu , Virginia Smith

Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its…

Computation and Language · Computer Science 2024-11-13 Wei Jie Yeo , Teddy Ferdinan , Przemyslaw Kazienko , Ranjan Satapathy , Erik Cambria

Large Reasoning Models (LRMs) generate structured chains of thought (CoTs) before producing final answers, making them especially vulnerable to knowledge leakage through intermediate reasoning steps. Yet, the memorization of sensitive…

Artificial Intelligence · Computer Science 2026-04-07 Tuan Le , Wei Qian , Mengdi Huai

Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which erases undesirable information during training, and…

Machine Learning · Computer Science 2026-05-19 Puning Yang , Junchi Yu , Qizhou Wang , Philip Torr , Bo Han , Xiuying Chen

Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from…

Cryptography and Security · Computer Science 2024-04-29 Kongyang Chen , Zixin Wang , Bing Mi , Waixi Liu , Shaowei Wang , Xiaojun Ren , Jiaxing Shen

Machine unlearning has garnered significant attention due to its ability to selectively erase knowledge obtained from specific training data samples in an already trained machine learning model. This capability enables data holders to…

Machine Learning · Computer Science 2024-03-13 Vinay Chakravarthi Gogineni , Esmaeil S. Nadimi