Papers knowledge editing
“knowledge editing” 태그가 달린 논문 288편 · 필터 해제
KLOD: Locality-Preserving Knowledge Editing via Non-Target Distribution Preservation
Fine-tuning-based knowledge editing is simple and architecture-agnostic, but standard cross-entropy increases the edited target probability without explicitly constraining changes in the non-target output distribution. I…
knowledge editingPersonaEdit: Representative Sample Selection for Personalized Model Editing
Personalization has attracted growing interest in LLM applications, yet existing retrieval-based approaches depend heavily on retrieval quality and degrade in long-term interactions. Model editing, which directly modifie…
knowledge editingLeveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs
As large language models (LLMs) are granted increasing autonomy, it is essential to investigate methods that can induce unsafe behavior. We propose a novel white-box attack inspired by locate-then-edit approaches from th…
knowledge editingHybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing
Large language models (LLMs) achieve remarkable performance across natural language tasks, yet they are trained on static corpora and their knowledge quickly becomes outdated in a fast-changing world. This motivates know…
knowledge editingForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models
Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understoo…
knowledge editingWeight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs
Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability. We introduce Weight-Adjusted Gradients (WAG), a simple yet effec…
knowledge editingMultimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing
Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors. E…
knowledge editingKnowledgeDebugger -- an Exploration Tool for Knowledge Localization and Editing in Transformers
Recent research has increasingly focused on understanding how Transformers store and process knowledge, as well as how this knowledge can be edited. Research work in this area is often conducted in two phases: first, phe…
knowledge editingReproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"
Fang et al. (2025) introduced a null-space constrained projection, named AlphaEdit, for locate-then-edit knowledge editing methods, theoretically guaranteeing that edits do not disrupt previously preserved knowledge, and…
knowledge editingExposing the Illusion of Erasure in Knowledge Editing for LLMs
Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly retraining, but its reliability and underlying mechanisms remain poorly understood. In this work, we examine KE from an …
knowledge editingOrthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs
Knowledge editing aims to efficiently update factual information in Large Language Models (LLMs) without full retraining. However, existing methods still suffer from performance degradation in batch knowledge editing. We…
knowledge editingLOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing
Lifelong knowledge editing aims to efficiently and sequentially update language models over time, as new knowledge becomes available or when the model makes mistakes, while preserving acceptable performance on past knowl…
knowledge editingWhen to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing
Knowledge editing systems must update selected facts while preserving nearby but irrelevant behavior. This paper studies this problem in a memory-assisted setting where an edit memory is retrieved at inference time and a…
knowledge editingTimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models
Masked diffusion language models (MDLMs) such as LLaDA now rival autoregressive (AR) LLMs, but every existing knowledge-editing and unlearning method (ROME, MEMIT, etc.) targets AR transformers and either makes assumptio…
knowledge editingBenchmarking Knowledge Editing using Logical Rules
Large Language Models (LLMs) are increasingly deployed in real-world applications that require access to up-to-date knowledge. However, retraining LLMs is computationally expensive. Therefore, knowledge editing technique…
knowledge editingCRANE: Knowledge Editing for Reasoning MLLMs
The emergence of reasoning multimodal large language models (MLLMs), which generate explicit chain-of-thought (CoT) reasoning before producing answers, has introduced a new challenge for knowledge editing: methods that a…
knowledge editingCan Factual Opinions Be Edited (Manipulated) in Large Language Models?
Large Language Models (LLMs) are increasingly integrated into various domains, making knowledge editing techniques crucial yet potentially hazardous. Current editing methods primarily target atomic facts, overlooking the…
knowledge editingHyperPatch: Sequential Knowledge Editing Under n-ary Structural Drift
Large Language Models (LLMs) rely on Knowledge Editing (KE) to maintain temporal validity, yet real-world knowledge is inherently n-ary. We demonstrate that in non-stationary environments, sequential updates to complex r…
Contrastive Learningknowledge editingKnowledge Editing in Masked Diffusion Language Models
Knowledge editing aims to update or correct factual knowledge in a language model. A widely used approach, locate-then-edit, does this in two steps: it first localizes a fact within the model, then edits the weights ther…
knowledge editingRevisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization
Single-edit updates in large language models can trigger ripple effects across local knowledge neighborhoods: desirable propagation to related facts and unintended perturbation of preserved ones. Existing methods address…
knowledge editing