相关论文: UniErase: Towards Balanced and Precise Unlearning …

Large Reasoning Models (LRMs) embed private or copyrighted information not only in their final answers but also throughout multi-step chain-of-thought (CoT) traces, making reliable unlearning far more demanding than in standard LLMs. We…

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While…

Large language models (LLMs) frequently memorize sensitive information during training, posing risks when deploying publicly accessible models. Current machine unlearning methods struggle to selectively remove specific data associations…

As privacy and security take center stage in AI, machine unlearning, the ability to erase specific knowledge from models, has garnered increasing attention. However, existing methods overly prioritize efficiency and aggressive forgetting,…

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…

Unified information extraction (UIE) aims to extract diverse structured information from unstructured text. While large language models (LLMs) have shown promise for UIE, they require significant computational resources and often struggle…

The development of Large Language Models (LLMs) faces a significant challenge: the exhausting of publicly available fresh data. This is because training a LLM needs a large demanding of new data. Federated learning emerges as a promising…

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In real-world scenarios, model owners…

The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on…

Large language models (LLMs) may memorize sensitive or copyrighted content, raising significant privacy and legal concerns. While machine unlearning has emerged as a potential remedy, prevailing paradigms rely on user-provided forget sets,…

Information removal or suppression in large language models (LLMs) is a desired functionality, useful in AI regulation, legal compliance, safety, and privacy. LLM unlearning methods aim to remove information on demand from LLMs. Current LLM…

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these…

LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain…

Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. However, we find that deterministic evaluations fail to capture…

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content…

Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. This ability to extract training data can be…

As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forgetting specific knowledge in training data, has been widely…

To address the growing demand for privacy protection in machine learning, we propose a novel and efficient machine unlearning approach for \textbf{L}arge \textbf{M}odels, called \textbf{LM}Eraser. Existing unlearning research suffers from…

We present the first comprehensive evaluation of cross-lingual unlearning in multilingual LLMs. Using translated TOFU benchmarks in seven language/script variants, we test major unlearning algorithms and show that most fail to remove facts…

Recent research has seen significant interest in methods for concept removal and targeted forgetting in text-to-image diffusion models. In this paper, we conduct a comprehensive white-box analysis showing the vulnerabilities in existing…