Related papers: A Comprehensive Evaluation of LLM Unlearning Robus…

Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspective for MU is presented upon low-dimensional feature…

Large Language Models (LLMs) are increasingly deployed in agentic and retrieval-augmented generation (RAG) systems, where they must execute user-specified tasks over externally provided reference text. In practice, such context is often…

While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particular, since models may store unsafe knowledge internally,…

Large Language Models (LLMs) are increasingly integrated into real-world applications, raising concerns about privacy, security and the need to remove undesirable knowledge. Machine Unlearning has emerged as a promising solution, yet faces…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…

In recent years, machine learning neural network has penetrated deeply into people's life. As the price of convenience, people's private information also has the risk of disclosure. The "right to be forgotten" was introduced in a timely…

Understanding whether and to what extent large language models (LLMs) have memorised training data has important implications for the reliability of their output and the privacy of their training data. In order to cleanly measure and…

While many recent methods aim to unlearn or remove knowledge from pretrained models, seemingly erased knowledge often persists and can be recovered in various ways. Because large foundation models are far from interpretable, understanding…

Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the…

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Validating Large Language Models with ReLM explores the application of formal languages to evaluate and control Large Language Models (LLMs) for memorization, bias, and zero-shot performance. Current approaches for evaluating these types…

Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase…

Large language models (LLMs) inherently absorb harmful knowledge, misinformation, and personal data during pretraining on large-scale web corpora, with no native mechanism for selective removal. While machine unlearning offers a principled…

Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…

Interactive reinforcement learning has allowed speeding up the learning process in autonomous agents by including a human trainer providing extra information to the agent in real-time. Current interactive reinforcement learning research has…

Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity, known as working memory, is fundamental to human reasoning and intelligence. Despite…

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…

Our interest is in the design of software systems involving a human-expert interacting -- using natural language -- with a large language model (LLM) on data analysis tasks. For complex problems, it is possible that LLMs can harness human…

Learned optimizers -- neural networks that are trained to act as optimizers -- have the potential to dramatically accelerate training of machine learning models. However, even when meta-trained across thousands of tasks at huge…