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.
Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening
Continual Learning for Large Language Models: A Survey
Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks
Neighboring Perturbations of Knowledge Editing on Large Language Models
SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering
From Understanding to Utilization: A Survey on Explainability for Large Language Models
DeepEdit: Knowledge Editing as Decoding with Constraints
Cross-lingual Editing in Multilingual Language Models
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
Editing Arbitrary Propositions in LLMs without Subject Labels
See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
MPN: Leveraging Multilingual Patch Neuron for Cross-lingual Model Editing
Large Language Models Relearn Removed Concepts
A Comprehensive Study of Knowledge Editing for Large Language Models
PokeMQA: Programmable knowledge editing for Multi-hop Question Answering
Retrieval-augmented Multilingual Knowledge Editing
MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA
Neuron-Level Knowledge Attribution in Large Language Models
History Matters: Temporal Knowledge Editing in Large Language Model
Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation
DemoCaricature: Democratising Caricature Generation with a Rough Sketch
Large Knowledge Model: Perspectives and Challenges
Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness
A-Scan2BIM: Assistive Scan to Building Information Modeling
DUnE: Dataset for Unified Editing
Continual Learning: Applications and the Road Forward
Flexible Model Interpretability through Natural Language Model Editing
Assessing Knowledge Editing in Language Models via Relation Perspective
Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers
Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications
Massive Editing for Large Language Models via Meta Learning
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.