Papers with Code 아카이브
Model Editing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
AnyEdit: Edit Any Knowledge Encoded in Language Models
Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject
Cross-Encoder Rediscovers a Semantic Variant of BM25
Position: Editing Large Language Models Poses Serious Safety Risks
Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge
Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach
Lifelong Knowledge Editing requires Better Regularization
Building Bridges, Not Walls -- Advancing Interpretability by Unifying Feature, Data, and Model Component Attribution
Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble
Knowledge Editing through Chain-of-Thought
Joint Knowledge Editing for Information Enrichment and Probability Promotion
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
ConceptEdit: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning
Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
Unveiling Concept Attribution in Diffusion Models
One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models
Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts
Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction
Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models
Model Editing for LLMs4Code: How Far are We?
Learning Where to Edit Vision Transformers
Reasons and Solutions for the Decline in Model Performance after Editing
Commonsense Knowledge Editing Based on Free-Text in LLMs
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
Should We Really Edit Language Models? On the Evaluation of Edited Language Models
Inference time LLM alignment in single and multidomain preference spectrum
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
Gradient Rewiring for Editable Graph Neural Network Training
Can Knowledge Editing Really Correct Hallucinations?
EcomEdit: An Automated E-commerce Knowledge Editing Framework for Enhanced Product and Purchase Intention Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.