Related papers: Memorization Sinks: Isolating Memorization during …

We explore a knowledge sanitization approach to mitigate the privacy concerns associated with large language models (LLMs). LLMs trained on a large corpus of Web data can memorize and potentially reveal sensitive or confidential…

Large Language Models (LLMs) are reshaping unsupervised learning by offering an unprecedented ability to perform text clustering based on their deep semantic understanding. However, their direct application is fundamentally limited by a…

Despite their powerful chat, coding, and reasoning abilities, Large Language Models (LLMs) frequently hallucinate. Conventional wisdom suggests that hallucinations are a consequence of a balance between creativity and factuality, which can…

Whether LLMs memorize their training data and what this means, from measuring privacy leakage to detecting copyright violations, has become a rapidly growing area of research. In the last few months, more than 10 new methods have been…

Large Language Models (LLMs) have become increasingly central to recommendation scenarios due to their remarkable natural language understanding and generation capabilities. Although significant research has explored the use of LLMs for…

Self-supervised learning (SSL) has recently received significant attention due to its ability to train high-performance encoders purely on unlabeled data-often scraped from the internet. This data can still be sensitive and empirical…

Large Language Models (LLMs) memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII), which should not be stored and, consequently, not leaked. In this paper, we introduce Private…

Neural networks pose a privacy risk to training data due to their propensity to memorise and leak information. Focusing on image classification, we show that neural networks also unintentionally memorise unique features even when they occur…

In this paper, we show that when spoken language models (SLMs) are instructed to speak in a specific speaking style at the beginning of a multi-turn conversation, they cannot maintain the required speaking styles after several turns of…

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…

Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-code human priors about what to store and how to revise memory, making them…

Large language models (LLMs) exhibit remarkable generative capabilities but raise ethical and security concerns by memorizing sensitive data, reinforcing biases, and producing harmful content. These risks have spurred interest in LLM…

Large language models (LLMs) have shown remarkable capabilities across various tasks, that are learned from massive amounts of text-based data. Although LLMs can control output sequence length, particularly in instruction-based settings,…

The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable…

Memorization in language models is widely studied but remains difficult to isolate and control. Understanding when and what models memorize is essential for explaining their predictions, yet existing approaches are post-hoc: they can detect…

Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of…

Large Language Model (LLM) unlearning has recently gained significant attention, driven by the need to remove unwanted information, such as private, sensitive, or copyrighted content, from LLMs. However, conventional unlearning approaches…

Large Language Models (LLMs) are known to memorize significant portions of their training data. Parts of this memorized content have been shown to be extractable by simply querying the model, which poses a privacy risk. We present a novel…

Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…

As the deployment of pre-trained language models (PLMs) expands, pressing security concerns have arisen regarding the potential for malicious extraction of training data, posing a threat to data privacy. This study is the first to provide a…