Papers Model Editing
“Model Editing” 태그가 달린 논문 193편 · 필터 해제
AnyEdit: Edit Any Knowledge Encoded in Language Models
Large language models (LLMs) often produce incorrect or outdated information, necessitating efficient and precise knowledge updates. Current model editing methods, however, struggle with long-form knowledge in diverse fo…
FormImage Editingknowledge editingModel EditingCross-Encoder Rediscovers a Semantic Variant of BM25
Neural Ranking Models (NRMs) have rapidly advanced state-of-the-art performance on information retrieval tasks. In this work, we investigate a Cross-Encoder variant of MiniLM to determine which relevance features it comp…
Information RetrievalModel EditingRetrievalPosition: Editing Large Language Models Poses Serious Safety Risks
Large Language Models (LLMs) contain large amounts of facts about the world. These facts can become outdated over time, which has led to the development of knowledge editing methods (KEs) that can change specific facts i…
knowledge editingModel EditingPositionEfficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach
Task vectors, which are derived from the difference between pre-trained and fine-tuned model weights, enable flexible task adaptation and model merging through arithmetic operations such as addition and negation. However…
Model EditingNegationTask ArithmeticBuilding Bridges, Not Walls -- Advancing Interpretability by Unifying Feature, Data, and Model Component Attribution
The increasing complexity of AI systems has made understanding their behavior a critical challenge. Numerous methods have been developed to attribute model behavior to three key aspects: input features, training data, an…
AttributeModel EditingEnhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
A Large Language Model (LLM) tends to generate inconsistent and sometimes contradictory outputs when presented with a prompt that has equivalent semantics but is expressed differently from the original prompt. To achieve…
Large Language ModelModel EditingModel OptimizationSeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation
Denoising diffusion probabilistic models have achieved significant success in point cloud generation, enabling numerous downstream applications, such as generative data augmentation and 3D model editing. However, lit…
3D GenerationData AugmentationDenoisingModel Editing+2Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to comply with evolving data regulations li…
image-classificationImage ClassificationMachine UnlearningModel EditingConcept-ROT: Poisoning Concepts in Large Language Models with Model Editing
Model editing methods modify specific behaviors of Large Language Models by altering a small, targeted set of network weights and require very little data and compute. These methods can be used for malicious applications…
MisinformationModel EditingModel-Editing-Based Jailbreak against Safety-aligned Large Language Models
Large Language Models (LLMs) have transformed numerous fields by enabling advanced natural language interactions but remain susceptible to critical vulnerabilities, particularly jailbreak attacks. Current jailbreak techn…
Model EditingSafety AlignmentUnveiling Concept Attribution in Diffusion Models
Diffusion models have shown remarkable abilities in generating realistic and high-quality images from text prompts. However, a trained model remains black-box; little do we know about the role of its components in exhibi…
Model EditingLifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts
Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenario…
knowledge editingMixture-of-ExpertsModel EditingSafety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction
Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. While model editing has been proposed to remo…
Image GenerationModel EditingModel Editing for LLMs4Code: How Far are We?
Large Language Models for Code (LLMs4Code) have been found to exhibit outstanding performance in the software engineering domain, especially the remarkable performance in coding tasks. However, even the most advanced LLM…
16kCode GenerationCode SummarizationContrastive Learning+5Learning Where to Edit Vision Transformers
Model editing aims to data-efficiently correct predictive errors of large pre-trained models while ensuring generalization to neighboring failures and locality to minimize unintended effects on unrelated examples. While …
Meta-LearningModel EditingObject RecognitionExpose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
Backdoor attacks covertly implant triggers into deep neural networks (DNNs) by poisoning a small portion of the training data with pre-designed backdoor triggers. This vulnerability is exacerbated in the era of large mod…
backdoor defenseModel EditingSST-2Should We Really Edit Language Models? On the Evaluation of Edited Language Models
Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelli…
General KnowledgeModel EditingInference time LLM alignment in single and multidomain preference spectrum
Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure. Existing training-time…
Model EditingPrompt EngineeringBackdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior o…
Adversarial AttackBackdoor AttackImage Captioningimage-classification+3Gradient Rewiring for Editable Graph Neural Network Training
Deep neural networks are ubiquitously adopted in many applications, such as computer vision, natural language processing, and graph analytics. However, well-trained neural networks can make prediction errors after deploy…
Graph Neural NetworkModel Editing