Papers with Code 아카이브

knowledge editing

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

1

보존된 평가 기록

2

코드

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

https://github.com/ABi-dot/Kedkg

공식 코드

Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering

https://github.com/Aries-chen/MedEditBench

공식 코드

Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing

https://github.com/BobXWu/AKEW

공식 코드

AKEW: Assessing Knowledge Editing in the Wild

https://github.com/Lyz1213/BadEdit

공식 코드

BadEdit: Backdooring large language models by model editing

https://github.com/MMKE-Bench-ICLR/MMKE-Bench

공식 코드

MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge

https://github.com/PinzhengWang322/Reveal_Attention_Drift

공식 코드

Revealing and Mitigating Over-Attention in Knowledge Editing

https://github.com/TrustedLLM/UnKE

공식 코드

Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models

https://github.com/XZhang00/LU-LAFNs

공식 코드

Multilingual Knowledge Editing with Language-Agnostic Factual Neurons

https://github.com/Zhow01/S2RKE

공식 코드

Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-Subject

https://github.com/acerkoo/disco

공식 코드

Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge

https://github.com/alessiogalatolo/diekae

공식 코드

DIEKAE: Difference Injection for Efficient Knowledge Augmentation and Editing of Large Language Models

https://github.com/applied-machine-learning-lab/mm4ke

공식 코드

Model Merging for Knowledge Editing

https://github.com/arvid-pku/atoke

공식 코드

History Matters: Temporal Knowledge Editing in Large Language Model

https://github.com/asdfo123/scedit

공식 코드

ScEdit: Script-based Assessment of Knowledge Editing

https://github.com/bebr2/editcot

공식 코드

Knowledge Editing through Chain-of-Thought

https://github.com/beepkh/unike

공식 코드

Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration

https://github.com/bigai-ai/ICE

공식 코드

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

https://github.com/byronbbl/deck

공식 코드

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts

https://github.com/chenhuihu/knowledge_in_superposition

공식 코드

Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models

https://github.com/chenhuihu/wilke

공식 코드

WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing

https://github.com/crashbugger/mindbridge

공식 코드

MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality

https://github.com/derekpowell/taxi

공식 코드

TAXI: Evaluating Categorical Knowledge Editing for Language Models

https://github.com/dtamayo-nlp/memat

공식 코드

Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge

https://github.com/ecnu-text-computing/knowledge-editing-benchmark

공식 코드

Benchmarking and Rethinking Knowledge Editing for Large Language Models

https://github.com/edenbiran/rippleedits

공식 코드

Evaluating the Ripple Effects of Knowledge Editing in Language Models

https://github.com/eric8932/jeep

공식 코드

Joint Knowledge Editing for Information Enrichment and Probability Promotion

https://github.com/google/belief-localization

공식 코드

Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models

https://github.com/hartvigsen-group/composable-interventions

공식 코드

Composable Interventions for Language Models

https://github.com/heng840/amig

공식 코드

Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons

https://github.com/hengrui-gu/pokemqa

공식 코드

PokeMQA: Programmable knowledge editing for Multi-hop Question Answering

https://github.com/hengrui-gu/t2iknowledgeediting

공식 코드

Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion

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

공식 코드

MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models

https://github.com/hiyouga/llama-factory

공식 코드

Time Sensitive Knowledge Editing through Efficient Finetuning

https://github.com/holi-lab/core

공식 코드

Context Robust Knowledge Editing for Language Models

https://github.com/huangxiusheng/dem

공식 코드

Commonsense Knowledge Editing Based on Free-Text in LLMs

https://github.com/jiakuan929/superficial-editing

공식 코드

Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing

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