Related papers: Beyond Sharp Minima: Robust LLM Unlearning via Fee…

Large Language Models (LLMs) trained on extensive datasets often learn sensitive information, which raises significant social and legal concerns under principles such as the "Right to be forgotten." Retraining entire models from scratch to…

Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data, however, this process might suffer from privacy issues and violations of data protection regulations. As a…

Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while maintaining general utility. However, existing approaches typically treat all tokens in a response indiscriminately and enforce uncertainty over…

Most value function learning algorithms in reinforcement learning are based on the mean squared (projected) Bellman error. However, squared errors are known to be sensitive to outliers, both skewing the solution of the objective and…

Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…

The literature has proposed various robust alternatives to empirical risk minimisation to address failure modes such as distribution shift, label noise and finite-sample degeneracies. Examples include distributionally robust optimization,…

As Large Language Models (LLMs) increasingly shape online content, removing targeted information from well-trained LLMs (also known as LLM unlearning) has become critical for web governance. A key challenge lies in sample-wise imbalance…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures. We challenge this belief…

Large language models trained on web-scale data can memorize private or sensitive knowledge, raising significant privacy risks. Although some unlearning methods mitigate these risks, they remain vulnerable to "relearning" during subsequent…

The need for machine unlearning is critical for data privacy, yet existing methods often cause Knowledge Contamination by unintentionally damaging related knowledge. Such a degraded model performance after unlearning has been recently…

Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to…

Machine unlearning, which selectively removes harmful knowledge from a pre-trained model without retraining from scratch, is crucial for addressing privacy, regulatory compliance, and ethical concerns in Large Language Models (LLMs).…

We introduce a novel machine unlearning framework founded upon the established principles of the min-max optimization paradigm. We capitalize on the capabilities of strong Membership Inference Attacks (MIA) to facilitate the unlearning of…

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Large Language Models (LLMs) have demonstrated strong capabilities in memorizing vast amounts of knowledge across diverse domains. However, the ability to selectively forget specific knowledge is critical for ensuring the safety and…

Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of isolated facts, often overlooking latent inferential…

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic…

Large language models (LLMs) exhibit exceptional performance but pose substantial privacy risks due to training data memorization, particularly within healthcare contexts involving imperfect or privacy-sensitive patient information. We…

Large language models (LLMs) serve as giant information stores, often including personal or copyrighted data, and retraining them from scratch is not a viable option. This has led to the development of various fast, approximate unlearning…