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/quqxui/medlasa

공식 코드

Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models

https://github.com/ruthless-man/awesome-learn-from-model

공식 코드

Learn From Model Beyond Fine-Tuning: A Survey

https://github.com/rymarinelli/leaking_lora

공식 코드

Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models

https://github.com/samyadeepbasu/locogen

공식 코드

On Mechanistic Knowledge Localization in Text-to-Image Generative Models

https://github.com/scalable-model-editing/gradual-catastrophic-forgetting

공식 코드

Model Editing at Scale leads to Gradual and Catastrophic Forgetting

https://github.com/scalable-model-editing/knowledge-editing-regularization

공식 코드

Lifelong Knowledge Editing requires Better Regularization

https://github.com/scalable-model-editing/rebuilding-rome

공식 코드

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

https://github.com/scalable-model-editing/unified-model-editing

공식 코드

A Unified Framework for Model Editing

https://github.com/shankarp8/knowledge_distillation

공식 코드

Propagating Knowledge Updates to LMs Through Distillation

https://github.com/silentview/emcid

공식 코드

Editing Massive Concepts in Text-to-Image Diffusion Models

https://github.com/sislab-unitn/dyknow

공식 코드

DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs

https://github.com/songxiaoshuai/postedit

공식 코드

Knowledge Editing on Black-box Large Language Models

https://github.com/stanfordnlp/pyvene

공식 코드

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

https://github.com/sycny/rae

공식 코드

Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering

https://github.com/syon-li/coachhook

공식 코드

Consecutive Batch Model Editing with HooK Layers

https://github.com/tal-aurorax/scen

공식 코드

Scalable Model Editing via Customized Expert Networks

https://github.com/thartvigsen/grace

공식 코드

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

https://github.com/thu-keg/event-level-knowledge-editing

공식 코드

Event-level Knowledge Editing

https://github.com/thunlp/eren

공식 코드

Robust and Scalable Model Editing for Large Language Models

https://github.com/tigerchen52/qrneuron

공식 코드

Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts

https://github.com/tonychenxyz/vit-interpret

공식 코드

Interpreting and Controlling Vision Foundation Models via Text Explanations

https://github.com/uiuctml/TaskVectorBasis

공식 코드

Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach

https://github.com/uppaal/detox-edit

공식 코드

Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity

https://github.com/vaidehi99/infodeletionattacks

공식 코드

Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

https://github.com/vicky-wil/remake

공식 코드

Retrieval-augmented Multilingual Knowledge Editing

https://github.com/vlkeb/vlkeb

공식 코드

VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark

https://github.com/wangyu-ustc/largescalewashing

공식 코드

Large Scale Knowledge Washing

https://github.com/wangyu-ustc/memoryllm

공식 코드

MEMORYLLM: Towards Self-Updatable Large Language Models

https://github.com/wangywust/deepedit

공식 코드

DeepEdit: Knowledge Editing as Decoding with Constraints

https://github.com/wanliyoung/collapse-in-model-editing

공식 코드

The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse

https://github.com/wanliyoung/revisit-editing-evaluation

공식 코드

The Mirage of Model Editing: Revisiting Evaluation in the Wild

https://github.com/weichuanw/llm-based-mt-via-model-editing

공식 코드

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing

https://github.com/weiyifan1023/RaKE

공식 코드

Assessing Knowledge Editing in Language Models via Relation Perspective

https://github.com/weiyifan1023/knowledge-edit-based-on-relation-perspective

공식 코드

Assessing Knowledge Editing in Language Models via Relation Perspective

https://github.com/xbmxb/edit_analysis

공식 코드

On the Robustness of Editing Large Language Models

https://github.com/xiaojiegu/ultraedit

공식 코드

UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models

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