相关论文: LLM Unlearning with LLM Beliefs

How does scaling the number of parameters in large language models (LLMs) affect their core capabilities? We study two natural scaling techniques -- weight pruning and simply training a smaller or larger model, which we refer to as dense…

Machine unlearning in the domain of large language models (LLMs) has attracted great attention recently, which aims to effectively eliminate undesirable behaviors from LLMs without full retraining from scratch. In this paper, we explore the…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}. LLM unlearning offers a principled approach to removing the influence of undesirable data…

Large Language Models (LLMs) have acquired ubiquitous attention for their performances across diverse domains. Our study here searches through LLMs' cognitive abilities and confidence dynamics. We dive deep into understanding the alignment…

Large language models (LLMs) require iterative updates to address the outdated information problem, where LLM unlearning offers an approach for selective removal. However, mainstream unlearning methods primarily rely on fine-tuning…

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…

Large language models (LLMs) suffer from hallucination and context forgetting. Prior studies suggest that attention drift is a primary cause of these problems, where LLMs' focus shifts towards newly generated tokens and away from the…

Advances in the general capabilities of large language models (LLMs) have led to their use for information retrieval, and as components in automated decision systems. A faithful representation of probabilistic reasoning in these models may…

Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from…

Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is…

Large language models learn and continually learn through the accumulation of gradient-based updates, but how individual pieces of new information affect existing knowledge, leading to both beneficial generalization and problematic…

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged as an efficient alternative to full retraining, aiming to…

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…

Recent research has revealed that deep neural networks often take dataset biases as a shortcut to make decisions rather than understand tasks, leading to failures in real-world applications. In this study, we focus on the spurious…

Long context reasoning in large language models (LLMs) has demonstrated enhancement of their cognitive capabilities via chain-of-thought (CoT) inference. Training such models is usually done via reinforcement learning with verifiable…

Natural language generation (NLG) is one of the most impactful fields in NLP, and recent years have witnessed its evolution brought about by large language models (LLMs). As the key instrument for writing assistance applications, they are…

Large language models (LLMs) should undergo rigorous audits to identify potential risks, such as copyright and privacy infringements. Once these risks emerge, timely updates are crucial to remove undesirable responses, ensuring legal and…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key method for improving Large Language Models' reasoning capabilities, yet recent evidence suggests it may paradoxically shrink the reasoning boundary rather than…