相关论文: Precise Localization of Memories: A Fine-grained N…

Large Language Models (LLMs) demonstrate exceptional capabilities in factual question answering, yet they sometimes provide incorrect responses. To address this issue, knowledge editing techniques have emerged as effective methods for…

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

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…

Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…

Brain localization, which describes the association between specific regions of the brain and their corresponding functions, is widely accepted in the field of cognitive science as an objective fact. Today's large language models (LLMs)…

As real-world knowledge evolves, the information embedded within large language models (LLMs) can become outdated, inadequate, or erroneous. Model editing has emerged as a prominent approach for updating LLMs' knowledge with minimal…

Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…

Model editing aims to efficiently alter the behavior of Large Language Models (LLMs) within a desired scope, while ensuring no adverse impact on other inputs. Recent years have witnessed various model editing methods been proposed. However,…

Model editing aims to enhance the accuracy and reliability of large language models (LLMs) by efficiently adjusting their internal parameters. Currently, most LLM editing datasets are confined to narrow knowledge domains and cover a limited…

Recent work in interpretability shows that large language models (LLMs) can be adapted for new tasks in a learning-free way: it is possible to intervene on LLM representations to elicit desired behaviors for alignment. For instance, adding…

Large language models (LLMs) are deployed on mobile devices to power killer applications such as intelligent assistants. LLMs pre-trained on general corpora often hallucinate when handling personalized or unseen queries, leading to…

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…

Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new facts into Large Language Models (LLMs). Two mainstream ME methods exist: parameter-modifying ME and parameter-preserving ME (integrating extra…

Large language models (LLMs) embed extensive knowledge and utilize it to perform exceptionally well across various tasks. Nevertheless, outdated knowledge or factual errors within LLMs can lead to misleading or incorrect responses, causing…

Large language models (LLMs) exhibit strong performance on factual recall and general reasoning but struggle to adapt to user-specific, commonsense knowledge, a challenge particularly acute in small-parameter settings where computational…

Knowledge Editing, which efficiently modifies the knowledge in large language models, has gathered great attention. Current benchmarks primarily use multi-hop question answering to assess and analyze newly injected or updated knowledge.…

Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness…

Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution techniques struggle to operate at neuron level. In this paper,…

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired…

Knowledge Editing (KE) aims to correct and update factual information in Large Language Models (LLMs) to ensure accuracy and relevance without computationally expensive fine-tuning. Though it has been proven effective in several domains,…