Papers Model Editing
“Model Editing” 태그가 달린 논문 193편 · 필터 해제
NAMET: Robust Massive Model Editing via Noise-Aware Memory Optimization
Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evalua…
AttributeModel EditingBalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
Large multi-modal models inevitably decay over time as facts change and previously learned information becomes outdated. Traditional approaches such as fine-tuning are often impractical for updating these models due to t…
knowledge editingModel EditingA Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented perfo…
Model EditingREDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models
The rapid advancement of generative AI highlights the importance of text-to-image (T2I) security, particularly with the threat of backdoor poisoning. Timely disclosure and mitigation of security vulnerabilities in T2I mo…
AttributeImage GenerationModel EditingWhen is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
Task arithmetic refers to editing the pre-trained model by adding a weighted sum of task vectors, each of which is the weight update from the pre-trained model to fine-tuned models for certain tasks. This approach recent…
Binary ClassificationDomain GeneralizationLarge Language ModelMachine Unlearning+4NAACL2025 Tutorial: Adaptation of Large Language Models
This tutorial on adaptation of LLMs is designed to address the growing demand for models that go beyond the static capabilities of generic LLMs by providing an overview of dynamic, domain-specific, and task-adaptive LLM …
Code GenerationModel EditingRAGRetrieval-augmented GenerationEfficient Model Editing with Task-Localized Sparse Fine-tuning
Task arithmetic has emerged as a promising approach for editing models by representing task-specific knowledge as composable task vectors. However, existing methods rely on network linearization to derive task vectors, l…
DisentanglementModel EditingNegationTask ArithmeticLocalized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching
This study investigates the localization of knowledge representation in fine-tuned GPT-2 models using Causal Layer Attribution via Activation Patching (CLAP), a method that identifies critical neural layers responsible f…
Answer GenerationEEGModel EditingLeaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models
To effectively deploy Large Language Models (LLMs) in application-specific settings, fine-tuning techniques are applied to enhance performance on specialized tasks. This process often involves fine-tuning on user data da…
Language ModelingLanguage ModellingLarge Language ModelModel EditingBiasEdit: Debiasing Stereotyped Language Models via Model Editing
Previous studies have established that language models manifest stereotyped biases. Existing debiasing strategies, such as retraining a model with counterfactual data, representation projection, and prompting often fail …
counterfactualLanguage ModelingLanguage ModellingModel EditingSPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. However, existing…
Model EditingExploiting Edited Large Language Models as General Scientific Optimizers
Large language models (LLMs) have been widely adopted in mathematical optimization in scientific scenarios for their extensive knowledge and advanced reasoning capabilities. Existing methods mainly focus on utilizing LLM…
Model EditingGeoEdit: Geometric Knowledge Editing for Large Language Models
Regular updates are essential for maintaining up-to-date knowledge in large language models (LLMs). Consequently, various model editing methods have been developed to update specific knowledge within LLMs. However, train…
General Knowledgeknowledge editingModel EditingA Causal Lens for Evaluating Faithfulness Metrics
Large Language Models (LLMs) offer natural language explanations as an alternative to feature attribution methods for model interpretability. However, despite their plausibility, they may not reflect the model's internal…
Decision MakingFact CheckingModel EditingObject CountingCoME: An Unlearning-based Approach to Conflict-free Model Editing
Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability. While model editing methods have been developed to address such errors without full re-tr…
Model EditingDELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
Large Language Models (LLMs) are widely applied in decision making, but their deployment is threatened by jailbreak attacks, where adversarial users manipulate model behavior to bypass safety measures. Existing defense m…
Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+3The Mirage of Model Editing: Revisiting Evaluation in the Wild
Despite near-perfect results in artificial evaluations, the effectiveness of model editing in real-world applications remains unexplored. To bridge this gap, we propose to study model editing in question answering (QA) b…
Model EditingQuestion AnsweringK-Edit: Language Model Editing with Contextual Knowledge Awareness
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 i…
Knowledge GraphsLanguage ModelingLanguage ModellingModel Editing+2Injecting Universal Jailbreak Backdoors into LLMs in Minutes
Jailbreak backdoor attacks on LLMs have garnered attention for their effectiveness and stealth. However, existing methods rely on the crafting of poisoned datasets and the time-consuming process of fine-tuning. In this w…
Model EditingReinforced Lifelong Editing for Language Models
Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time. Model editing addresses this challenge by modifying model parameters wit…
Model Editing