Papers with Code 아카이브

Model Editing

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/jianghoucheng/nse

공식 코드

Neuron-Level Sequential Editing for Large Language Models

https://github.com/john-hewitt/model-editing-canonical-examples

공식 코드

Model Editing with Canonical Examples

https://github.com/johnnychanv/JailbreakEdit

공식 코드

Injecting Universal Jailbreak Backdoors into LLMs in Minutes

https://github.com/jometeorie/multihopshortcuts

공식 코드

Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models

https://github.com/kawakera-lab/crossmodeltransfer

공식 코드

Cross-Model Transfer of Task Vectors via Few-Shot Orthogonal Alignment

https://github.com/keltin13/concept-rot

공식 코드

Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

https://github.com/kmeng01/rome

공식 코드

Locating and Editing Factual Associations in GPT

https://github.com/krystalan/bi_zsre

공식 코드

Cross-Lingual Knowledge Editing in Large Language Models

https://github.com/leo-liuzy/propmend

공식 코드

PropMEND: Hypernetworks for Knowledge Propagation in LLMs

https://github.com/lingo-iitgn/xme

공식 코드

Cross-lingual Editing in Multilingual Language Models

https://github.com/lins-lab/collabedit

공식 코드

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

https://github.com/lliutianc/roselora

공식 코드

RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning

https://github.com/llm-editing/HalluEditBench

공식 코드

Can Knowledge Editing Really Correct Hallucinations?

https://github.com/lqinfdim/editingevaluation

공식 코드

Should We Really Edit Language Models? On the Evaluation of Edited Language Models

https://github.com/machelreid/editpro

공식 코드

Learning to Model Editing Processes

https://github.com/madrylab/modelcomponents

공식 코드

Decomposing and Editing Predictions by Modeling Model Computation

https://github.com/mail-research/cad-attribution4diffusion

공식 코드

Unveiling Concept Attribution in Diffusion Models

https://github.com/mcgill-nlp/logicalknowedit

공식 코드

Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness

https://github.com/miulab/editllm-survey

공식 코드

Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models

https://github.com/mjy1111/bake

공식 코드

Untying the Reversal Curse via Bidirectional Language Model Editing

https://github.com/mjy1111/peak

공식 코드

Neighboring Perturbations of Knowledge Editing on Large Language Models

https://github.com/mjy1111/prune

공식 코드

Perturbation-Restrained Sequential Model Editing

https://github.com/nbahador/-fine_tuned_gpt2_model_on_epilepsy_related_pubmed_abstracts

공식 코드

Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching

https://github.com/nervjack2/propertyneurons

공식 코드

Property Neurons in Self-Supervised Speech Transformers

https://github.com/nlpkeg/D4S

공식 코드

Reasons and Solutions for the Decline in Model Performance after Editing

https://github.com/opanhw/FiNE

공식 코드

Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs

https://github.com/opanhw/MM_Neurons

공식 코드

Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers

https://github.com/ouxiang-li/speed

공식 코드

SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models

https://github.com/pkunlp-icler/ike

공식 코드

Can We Edit Factual Knowledge by In-Context Learning?

https://github.com/princeton-nlp/mquake

공식 코드

MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

https://github.com/qilimk/biggan-am

공식 코드

A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings

https://github.com/qinghua-zhou/stealth-edits

공식 코드

Stealth edits to large language models

https://github.com/qiuzh20/tuning-keys-v.s.-values

공식 코드

Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers

https://github.com/qizhou000/DAFNet

공식 코드

DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models

https://github.com/qizhou000/RECIPE

공식 코드

Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning

https://github.com/qizhou000/visedit

공식 코드

Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.