相关论文: Explainable LLM Unlearning Through Reasoning

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Large Language Models (LLMs) have highlighted the necessity of effective unlearning mechanisms to comply with data regulations and ethical AI practices. LLM unlearning aims at removing undesired data influences and associated model…

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques…

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…

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance,…

Due to increasing privacy regulations and regulatory compliance, Machine Unlearning (MU) has become essential. The goal of unlearning is to remove information related to a specific class from a model. Traditional approaches achieve exact…

With the implementation of personal data privacy regulations, the field of machine learning (ML) faces the challenge of the "right to be forgotten". Machine unlearning has emerged to address this issue, aiming to delete data and reduce its…

Pre-trained Vision-Language Models (VLMs) exhibit strong generalization capabilities, enabling them to recognize a wide range of objects across diverse domains without additional training. However, they often retain irrelevant information…

Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge remains an open question. We study this question in a controlled zero-shot, one-hop,…

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and robustly -- the hallmarks of artificial general intelligence…

When introducing Large Language Models (LLMs) into industrial applications, such as healthcare and education, the risk of generating harmful content becomes a significant challenge. While existing machine unlearning methods can erase…

Understanding and shaping the behaviour of Large Language Models (LLMs) is increasingly important as applications become more powerful and more frequently adopted. This paper introduces a machine unlearning method specifically designed for…

Unlearning in Large Language Models (LLMs) is essential for ensuring ethical and responsible AI use, especially in addressing privacy leak, bias, safety, and evolving regulations. Existing approaches to LLM unlearning often rely on retain…

Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed…

Student simulation can support learning-by-teaching pedagogy where human students (as tutors) teach AI-simulated novice students (as tutees). Recent research often relies on prompt engineering with large language models (LLMs) to simulate…

State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Consequently, Content Removal Techniques (CRTs) have emerged as a…

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive…

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine unlearning for large language models (LLMs) aims to remove targeted knowledge while preserving general capability. In this paper, we recast LLM unlearning as an asymmetric two-task problem: retention is the primary objective and…