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/xinhaoyi/edit_bio_long_tail

공식 코드

Can We Edit LLMs for Long-Tail Biomedical Knowledge?

https://github.com/xpq-tech/code-llmedit

공식 코드

Model Editing for LLMs4Code: How Far are We?

https://github.com/xpq-tech/keti

공식 코드

Identifying Knowledge Editing Types in Large Language Models

https://github.com/xpq-tech/pmet

공식 코드

PMET: Precise Model Editing in a Transformer

https://github.com/xpq-tech/swea

공식 코드

SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering

https://github.com/yaohui120/comprehendedit

공식 코드

ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing

https://github.com/ybdai7/NAMET-massive-editing

공식 코드

NAMET: Robust Massive Model Editing via Noise-Aware Memory Optimization

https://github.com/yjiangcm/lte

공식 코드

Learning to Edit: Aligning LLMs with Knowledge Editing

https://github.com/zce1112zslx/ike

공식 코드

Can We Edit Factual Knowledge by In-Context Learning?

https://github.com/zepingyu0512/arithmetic-mechanism

공식 코드

Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis

https://github.com/zepingyu0512/neuron-attribution

공식 코드

Neuron-Level Knowledge Attribution in Large Language Models

https://github.com/zeroyuhuang/transformer-patcher

공식 코드

Transformer-Patcher: One Mistake worth One Neuron

https://github.com/zhang-yihao/adversarial-representation-engineering

공식 코드

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models

https://github.com/zhaozetong/dualedit

공식 코드

Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs

https://github.com/zhimengj0326/gradient_rewiring_editing

공식 코드

Gradient Rewiring for Editable Graph Neural Network Training

https://github.com/zhrli324/rledit

공식 코드

Reinforced Lifelong Editing for Language Models

https://github.com/zjunlp/BiasEdit

공식 코드

BiasEdit: Debiasing Stereotyped Language Models via Model Editing

https://github.com/zjunlp/PromptKG/tree/main/deltaKG

공식 코드

Editing Language Model-based Knowledge Graph Embeddings

https://github.com/zjunlp/cake

공식 코드

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners

https://github.com/zjunlp/easyedit

공식 코드

Editing Large Language Models: Problems, Methods, and Opportunities

https://github.com/zjunlp/knowledgecircuits

공식 코드

Knowledge Circuits in Pretrained Transformers

https://github.com/zjunlp/knowledgeeditingpapers

공식 코드

A Comprehensive Study of Knowledge Editing for Large Language Models

https://github.com/zjunlp/knowlm

공식 코드

EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models

https://github.com/zjunlp/oneedit

공식 코드

OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System

https://github.com/zjunlp/pitfallsknowledgeediting

공식 코드

Unveiling the Pitfalls of Knowledge Editing for Large Language Models

https://github.com/zjunlp/promptkg

공식 코드

Editing Language Model-based Knowledge Graph Embeddings

https://github.com/zongkaiz/fleke

공식 코드

FLEKE: Federated Locate-then-Edit Knowledge Editing

https://github.com/zzhao71/ripplecot

공식 코드

RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning

https://huggingface.co/datasets/SoftMINER-Group/NicheHazardQA

공식 코드

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models

https://huggingface.co/datasets/SoftMINER-Group/TechHazardQA

공식 코드

How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries

https://gitee.com/zhengkeli/zkl-knowedit-rome

Locating and Editing Factual Associations in GPT

https://github.com/EVOKE-LMM/EVOKE

In-Context Editing: Learning Knowledge from Self-Induced Distributions

https://github.com/dmis-lab/temporalhead

Knowledge Circuits in Pretrained Transformers

https://github.com/eric-mitchell/serac

Fast Model Editing at Scale

https://github.com/frankaging/pyvene

pyvene: A Library for Understanding and Improving PyTorch Models via Interventions

https://github.com/hi-archers/stableke

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

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