Related papers: SUIT: Knowledge Editing with Subspace-Aware Key-Va…

Large language models are often expected to constantly adapt to new sources of knowledge and knowledge editing techniques aim to efficiently patch the outdated model knowledge, with minimal modification. Most prior works focus on…

Knowledge editing is pivotal for efficiently updating the parametric memory of Large Language Models (LLMs), enabling them to function as evolving agents in dynamic environments. However, mainstream in-parameter knowledge editing approaches…

As the cost associated with fine-tuning Large Language Models (LLMs) continues to rise, recent research efforts have pivoted towards developing methodologies to edit implicit knowledge embedded within LLMs. Yet, there's still a dark cloud…

Adapting CLIP to vertical domains is typically approached by novel fine-tuning strategies or by continual pre-training (CPT) on large domain-specific datasets. Yet, data itself remains an underexplored factor in this process. We revisit…

In-context knowledge editing (IKE) enables efficient modification of large language model (LLM) outputs without parameter changes and at zero-cost. However, it can be misused to manipulate responses opaquely, e.g., insert misinformation or…

Knowledge Editing (KE) enables the modification of outdated or incorrect information in large language models (LLMs). While existing KE methods can update isolated facts, they often fail to generalize these updates to multi-hop reasoning…

Recent advances in language model interpretability have identified circuits, critical subnetworks that replicate model behaviors, yet how knowledge is structured within these crucial subnetworks remains opaque. To gain an understanding…

Large language models (LLMs) have recently transformed both the academic and industrial landscapes due to their remarkable capacity to understand, analyze, and generate texts based on their vast knowledge and reasoning ability.…

Language Models (LMs) have become widely used in software engineering, especially for tasks such as code generation, where they are referred to as code LMs. These models have proven effective in generating code, making it easier for…

Incorrect information poses significant challenges by disrupting content veracity and integrity, yet most detection approaches struggle to jointly balance textual content verification with external knowledge modification under collapsed…

Large language models (LLMs) have recently emerged as powerful training-free recommenders. However, their knowledge of individual items is inevitably uneven due to imbalanced information exposure during pretraining, a phenomenon we refer to…

Knowledge editing aims to efficiently update Large Language Models (LLMs) by modifying specific knowledge without retraining the entire model. Among knowledge editing approaches, in-context editing (ICE) offers a lightweight solution by…

As real-world knowledge is constantly evolving, ensuring the timeliness and accuracy of a model's knowledge is crucial. This has made knowledge editing in large language models increasingly important. However, existing knowledge editing…

Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current approaches to address this issue involve costly dataset…

Recently, large language models (LLMs) have demonstrated impressive results but still suffer from hallucinations. Model editing has been proposed to correct factual inaccuracies in LLMs. A challenging case is sequential model editing (SME),…

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…

Machine learning models are commonly used for malware classification; however, they suffer from performance degradation over time due to concept drift. Adapting these models to changing data distributions requires frequent updates, which…

Model editing techniques modify a minor proportion of knowledge in Large Language Models (LLMs) at a relatively low cost, which have demonstrated notable success. Existing methods assume Transformer Layer (TL) hidden states are values of…

Large Language Models (LLMs) internalize vast world knowledge as parametric memory, yet inevitably inherit the staleness and errors of their source corpora. Consequently, ensuring the reliability and malleability of these internal…

Model editing aims to correct errors and outdated knowledge in the Large language models (LLMs) with minimal cost. Prior research has proposed a variety of datasets to assess the effectiveness of these model editing methods. However, most…