Related papers: Locate-then-edit for Multi-hop Factual Recall unde…
Detecting factual errors in textual information, whether generated by large language models (LLM) or curated by humans, is crucial for making informed decisions. LLMs' inability to attribute their claims to external knowledge and their…
Large language models store not only isolated facts but also rules that support reasoning across symbolic expressions, natural language explanations, and concrete instances. Yet most model editing methods are built for fact-level knowledge,…
While Large Vision-Language Models (LVLMs) offer powerful capabilities, they pose privacy risks by unintentionally memorizing sensitive personal information. Current unlearning benchmarks attempt to mitigate this using fictitious identities…
The proliferation of fake news has had far-reaching implications on politics, the economy, and society at large. While Fake news detection methods have been employed to mitigate this issue, they primarily depend on two essential elements:…
Large Language Models (LLMs) store an extensive amount of factual knowledge obtained from vast collections of text. To effectively utilize these models for downstream tasks, it is crucial to have reliable methods for measuring their…
As the world changes, we need to be able to update our models and correct false information without costly retraining. Knowledge-based model editing enables precise modifications to the weights of large language models in order to modify…
Knowledge editing techniques have emerged as essential tools for updating the factual knowledge of large language models (LLMs) and multimodal models (LMMs), allowing them to correct outdated or inaccurate information without retraining…
Recent advances in Knowledge Editing (KE), particularly Rank-One Model Editing (ROME), show superior efficiency over fine-tuning and in-context learning for updating single-hop facts in transformers. However, these methods face significant…
The potential of using a large language model (LLM) as a knowledge base (KB) has sparked significant interest. To manage the knowledge acquired by LLMs, we need to ensure that the editing of learned facts respects internal logical…
Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited…
Lifelong knowledge editing enables continuous, precise updates to outdated knowledge in large language models (LLMs) without computationally expensive full retraining. However, existing methods often accumulate errors throughout the editing…
Language models learn a great quantity of factual information during pretraining, and recent work localizes this information to specific model weights like mid-layer MLP weights. In this paper, we find that we can change how a fact is…
Large language models (LLMs) are pretrained on corpora containing trillions of tokens and, therefore, inevitably memorize sensitive information. Locate-then-edit methods, as a mainstream paradigm of model editing, offer a promising solution…
Multimodal Large Language Models (MLLMs), such as GPT4o, have shown strong capabilities in visual reasoning and explanation generation. However, despite these strengths, they face significant challenges in the increasingly critical task of…
Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs). In this work, we focus on Same-Subject Editing, which involves modifying multiple attributes of a…
Visual Language Models (VLMs) are powerful generative tools but often produce factually inaccurate outputs due to a lack of robust reasoning capabilities. While extensive research has been conducted on integrating external knowledge for…
Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic…
Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring…
Large language models (LLMs) can recall a wide range of factual knowledge across languages. However, existing factual recall evaluations primarily assess fact retrieval in isolation, where the queried entity is explicitly named and the fact…
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…